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. 43654
    Prev
    Next
    INDEX
    Explanations

    number

    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
     Paras
    -0.08
    ('{}
    -0.07
     tightening
    -0.07
     Genel
    -0.07
    形式
    -0.07
     fetal
    -0.07
    理由
    -0.07
     presence
    -0.07
     anten
    -0.07
     offici
    -0.07
    POSITIVE LOGITS
    是多少
    0.09
     narciss
    0.09
     જેના
    0.09
     borrowed
    0.09
    _Integer
    0.08
     referred
    0.08
     burglar
    0.08
    $value
    0.08
    Reusable
    0.08
    .Integer
    0.08
    Activations Density 0.040%

    No Known Activations