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. 12411
    Prev
    Next
    INDEX
    Explanations

    机

    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
     fir
    -0.08
     liz
    -0.08
     pist
    -0.08
    _preds
    -0.08
    Fir
    -0.08
     solids
    -0.08
     Pale
    -0.08
    	Table
    -0.08
     shelf
    -0.08
    (dic
    -0.07
    POSITIVE LOGITS
    ustomer
    0.09
    eme
    0.08
    ومی
    0.07
    óttir
    0.07
     Благ
    0.07
     mission
    0.07
     SNP
    0.07
    �
    0.07
    ović
    0.07
    .amazonaws
    0.07
    Activations Density 0.000%

    No Known Activations