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. 77508
    Prev
    Next
    INDEX
    Explanations

    hardware resources

    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
     censor
    -0.09
     ചേര്
    -0.08
     ajan
    -0.08
     添加
    -0.08
     concatenate
    -0.08
    Michel
    -0.08
     जोड
    -0.07
     subtil
    -0.07
     hinzufügen
    -0.07
     சேர
    -0.07
    POSITIVE LOGITS
     lesión
    0.09
     зах
    0.08
    সূচ
    0.08
     allocated
    0.08
     allocate
    0.08
     patroon
    0.08
    يفة
    0.08
     damages
    0.08
     القدس
    0.08
     확보
    0.08
    Activations Density 0.003%

    No Known Activations