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. 65573
    Prev
    Next
    INDEX
    Explanations

    period

    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
     Tours
    -0.08
    ,加
    -0.08
     Sty
    -0.07
     ár
    -0.07
     Naturally
    -0.07
     الحال
    -0.07
     vectors
    -0.07
    ീസ്
    -0.07
     tours
    -0.07
    icular
    -0.07
    POSITIVE LOGITS
    200
    0.10
    199
    0.09
    年度
    0.09
    201
    0.09
    XXXXX
    0.08
    _ib
    0.08
    XXXX
    0.08
     INT
    0.08
    202
    0.08
    २०१
    0.08
    Activations Density 0.002%

    No Known Activations