Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 113069
    Prev
    Next
    INDEX
    Explanations

    self-harm

    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
     pouvoir
    -0.09
     GDPR
    -0.07
     essence
    -0.07
     Grâce
    -0.07
     gennem
    -0.07
     mondial
    -0.07
     Brasileiro
    -0.07
    ствовать
    -0.07
    vents
    -0.07
     molte
    -0.07
    POSITIVE LOGITS
    煤
    0.09
     pancre
    0.08
    .dropout
    0.08
     suicide
    0.08
     knee
    0.08
     haj
    0.08
     realización
    0.08
     suicidal
    0.08
    Withdrawal
    0.08
     initiating
    0.08
    Activations Density 0.010%

    No Known Activations