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. 3-RESID-POST-AA
    6. 12294
    Prev
    Next
    INDEX
    Explanations

    word

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     averages
    -0.08
     averaged
    -0.07
     centrales
    -0.07
    例如
    -0.07
    呈
    -0.07
    _EXPR
    -0.07
     workloads
    -0.07
    δει
    -0.07
    tré
    -0.07
    operator
    -0.07
    POSITIVE LOGITS
     Nora
    0.09
     pand
    0.09
     лі
    0.08
     ontvangst
    0.08
     듣
    0.08
    ಾಲಯ
    0.08
    Remarks
    0.08
     강
    0.08
     thereto
    0.08
    mys
    0.08
    Activations Density 0.009%

    No Known Activations