© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 102779
    Prev
    Next
    INDEX
    Explanations

    commas

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ----------------------------------------------------------------
    -0.12
    ////////////////////////////////////////////////////////////////////////////
    -0.11
     //////////////////////////////////////////////////////////////////
    -0.11
    ................................
    -0.11
    ------------↵
    -0.10
     //////////////////////////////////
    -0.10
     ----------------
    -0.10
    ////////////////////////////////////////////////////////////////////////
    -0.10
    ////////////////////////////////////////////////////////////////////
    -0.10
    ////////////////////////////////////////////////////////////////
    -0.10
    POSITIVE LOGITS
     diced
    0.09
     assorted
    0.09
     ample
    0.09
     milk
    0.08
     Shimano
    0.08
     DJI
    0.08
     Toyota
    0.08
     \
↵
    0.08
     turmeric
    0.08
     plenty
    0.08
    Activations Density 0.015%

    No Known Activations