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. 76351
    Prev
    Next
    INDEX
    Explanations

    Russian conjugations

    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
     finir
    -0.08
    (make
    -0.08
    _est
    -0.08
    estate
    -0.08
    -maker
    -0.07
    -0.07
     ,
    -0.07
    fiction
    -0.07
     Cun
    -0.07
    -est
    -0.07
    POSITIVE LOGITS
     exactamente
    0.08
    .Serialized
    0.08
    والي
    0.08
    Generally
    0.07
     concret
    0.07
    ിരിക്കുന്ന
    0.07
    σιο
    0.07
    nikov
    0.07
     razon
    0.07
    ല്ല
    0.07
    Activations Density 0.018%

    No Known Activations