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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 30841
    Prev
    Next
    INDEX
    Explanations

    electricity transmission

    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
     ethos
    -0.08
    Tokenizer
    -0.08
    Models
    -0.07
    Theme
    -0.07
    ишь
    -0.07
    _models
    -0.07
    /themes
    -0.07
    models
    -0.07
    Authenticator
    -0.07
    after
    -0.07
    POSITIVE LOGITS
     Fc
    0.09
     offshore
    0.09
     Sexy
    0.08
     ジ
    0.08
     Благодаря
    0.08
     北
    0.08
     மல
    0.08
     ASEAN
    0.08
     Offshore
    0.08
     Fuk
    0.08
    Activations Density 0.001%

    No Known Activations