© 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. 3-RESID-POST-AA
    11. 1294
    Prev
    Next
    INDEX
    Explanations

    sold

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    elem
    -0.07
    onom
    -0.07
     �
    -0.07
    hole
    -0.07
     plut
    -0.07
     interfer
    -0.07
     진
    -0.07
     ప్రక
    -0.07
     stupidity
    -0.07
    Outer
    -0.07
    POSITIVE LOGITS
     Vegas
    0.08
     Dro
    0.08
    �
    0.08
     sing
    0.07
     rearr
    0.07
     meltdown
    0.07
     ace
    0.07
     bán
    0.07
    给
    0.07
     lanc
    0.07
    Activations Density 0.023%

    No Known Activations