© 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. 23-RESID-POST-AA
    11. 5999
    Prev
    Next
    INDEX
    Explanations

    Content Security Policy

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tetas
    -0.09
     causada
    -0.09
     blowjob
    -0.09
     النبات
    -0.09
     Sexy
    -0.08
     Ownership
    -0.08
     prostitutes
    -0.08
     shemale
    -0.08
    achuset
    -0.08
    ிப்ப
    -0.08
    POSITIVE LOGITS
     cd
    0.12
    cdnjs
    0.12
     font
    0.12
    font
    0.11
    nonce
    0.11
    .font
    0.11
     fonts
    0.10
    frame
    0.10
     worker
    0.10
    fonts
    0.10
    Activations Density 0.002%

    No Known Activations