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. 30008
    Prev
    Next
    INDEX
    Explanations

    describing

    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
     Todas
    -0.09
    _All
    -0.08
    Todas
    -0.08
     Código
    -0.08
     Matr
    -0.08
    _BIN
    -0.08
    Su
    -0.08
     toutes
    -0.08
     Su
    -0.08
     Categoria
    -0.08
    POSITIVE LOGITS
     भ
    0.09
     vividly
    0.09
    如何
    0.08
     happenings
    0.08
     כיצד
    0.08
    留
    0.08
     vivid
    0.07
     glowing
    0.07
     aloud
    0.07
    557
    0.07
    Activations Density 0.014%

    No Known Activations