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. 61013
    Prev
    Next
    INDEX
    Explanations

    of

    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
    Bild
    -0.08
    comod
    -0.08
    haar
    -0.08
    Hz
    -0.08
    (Edit
    -0.08
     merkez
    -0.08
    Metric
    -0.08
    uevo
    -0.08
     Mutual
    -0.08
    meric
    -0.08
    POSITIVE LOGITS
     reasoning
    0.12
     deduct
    0.09
     steps
    0.08
     الحساب
    0.08
     opa
    0.08
     inference
    0.08
     workings
    0.08
     deduction
    0.08
     intermediate
    0.08
    步骤
    0.08
    Activations Density 0.404%

    No Known Activations