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. 76686
    Prev
    Next
    INDEX
    Explanations

    -yl

    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
     kih
    -0.08
     domest
    -0.08
     нуж
    -0.07
     правильно
    -0.07
    ,row
    -0.07
    ом
    -0.07
     wi
    -0.07
     Bonn
    -0.07
     лично
    -0.07
    �
    -0.07
    POSITIVE LOGITS
     rota
    0.09
     odont
    0.08
    佛
    0.08
     mídia
    0.08
     cocktail
    0.08
     ആക്രമ
    0.08
    æg
    0.07
    dance
    0.07
    .Display
    0.07
     claws
    0.07
    Activations Density 0.000%

    No Known Activations