© 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. 7-RESID-POST-AA
    11. 1268
    Prev
    Next
    INDEX
    Explanations

    opinions and arguments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     중
    -0.09
     bzw
    -0.08
    и
    -0.08
    傅
    -0.08
     prob
    -0.07
     podczas
    -0.07
     опы
    -0.07
     있는데
    -0.07
     해당
    -0.07
    第四
    -0.07
    POSITIVE LOGITS
     arz
    0.10
     ration
    0.09
     craving
    0.08
     societal
    0.08
    whatever
    0.08
     rightly
    0.08
     racional
    0.08
     niður
    0.08
     willst
    0.08
     exhaustion
    0.08
    Activations Density 1.275%

    No Known Activations