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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 12685
    Prev
    Next
    INDEX
    Explanations

    is are

    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
     CE
    -0.08
    .wordpress
    -0.07
     anten
    -0.07
    _PA
    -0.07
    _FA
    -0.07
    .ft
    -0.07
     VAT
    -0.07
     climax
    -0.07
     valleys
    -0.07
     chlor
    -0.07
    POSITIVE LOGITS
     coef
    0.09
     তখন
    0.08
     অনুম
    0.08
    整数
    0.08
     satisfacer
    0.08
     স্থানীয়
    0.08
     સ્વ
    0.08
     যথ
    0.08
     integers
    0.08
    »
    0.08
    Activations Density 0.028%

    No Known Activations