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. 54187
    Prev
    Next
    INDEX
    Explanations

    mal

    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
     function
    -0.08
    abled
    -0.07
     adult
    -0.07
     wholesale
    -0.07
     holder
    -0.07
    理由
    -0.07
    abler
    -0.07
     array
    -0.07
     emi
    -0.07
     multim
    -0.07
    POSITIVE LOGITS
    ге
    0.09
     вашу
    0.09
     بحران
    0.08
    гра
    0.08
     безопасность
    0.08
     resistência
    0.08
    גב
    0.08
     éste
    0.08
     секрет
    0.08
     געד
    0.08
    Activations Density 0.503%

    No Known Activations