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. 43106
    Prev
    Next
    INDEX
    Explanations

    Math, parsing, and translation

    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
    Oper
    -0.08
     Hopper
    -0.07
    opc
    -0.07
    /screens
    -0.07
    _generation
    -0.07
    strconv
    -0.07
    性交
    -0.07
    olino
    -0.07
    -generation
    -0.07
     રહ્યો
    -0.07
    POSITIVE LOGITS
    끼
    0.07
    ాయని
    0.07
     vissa
    0.07
     later
    0.07
    _SUM
    0.07
     نفس
    0.07
     dann
    0.07
    043
    0.07
    ipelines
    0.07
    ابعة
    0.07
    Activations Density 0.043%

    No Known Activations