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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 110662
    Prev
    Next
    INDEX
    Explanations

    Elaboration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _orig
    -0.08
    _prob
    -0.07
    _unknown
    -0.07
     West
    -0.07
    ="#">
    -0.07
     sam
    -0.07
     influ
    -0.07
     factors
    -0.07
     entsprechen
    -0.07
     ancestry
    -0.07
    POSITIVE LOGITS
     endlessly
    0.13
     intermin
    0.11
     хват
    0.10
     einzelne
    0.10
     მთელი
    0.10
     долго
    0.10
     besteed
    0.10
     pouvait
    0.10
     awhile
    0.09
     länge
    0.09
    Activations Density 0.035%

    No Known Activations