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. 24384
    Prev
    Next
    INDEX
    Explanations

    book excerpts

    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
    代理
    -0.08
     fetch
    -0.07
     나
    -0.07
     Ford
    -0.07
     وړاندې
    -0.07
    .nu
    -0.07
     nu
    -0.07
    рон
    -0.07
    \n
    -0.07
     રાજ
    -0.07
    POSITIVE LOGITS
     Nota
    0.09
    absch
    0.09
     Ensino
    0.09
     elaborado
    0.09
     Rever
    0.08
     Joining
    0.08
     Progn
    0.08
     Historia
    0.08
     Encryption
    0.08
     Recre
    0.08
    Activations Density 0.000%

    No Known Activations