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. 76485
    Prev
    Next
    INDEX
    Explanations

    error return values

    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
     المغ
    -0.09
     музыку
    -0.09
     وسائل
    -0.08
    .bundle
    -0.08
     الموس
    -0.08
    :utf
    -0.08
     outreach
    -0.08
    .span
    -0.08
     வெள
    -0.08
    _helpers
    -0.08
    POSITIVE LOGITS
    返回
    0.09
    	Return
    0.08
     paranoid
    0.08
     corrupt
    0.08
     prever
    0.08
     wicker
    0.08
     doubtful
    0.08
     fals
    0.08
     dönüş
    0.08
     beheer
    0.08
    Activations Density 0.004%

    No Known Activations