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. 11602
    Prev
    Next
    INDEX
    Explanations

    Question phrasing

    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
    <|reserved_200016|>
    -0.08
    wr
    -0.07
    ningen
    -0.07
    عت
    -0.07
    ning
    -0.07
     വെള്ള
    -0.07
    וחים
    -0.07
    tegration
    -0.07
    -memory
    -0.07
     इनके
    -0.07
    POSITIVE LOGITS
     Balcony
    0.08
     прибыль
    0.08
    apatan
    0.08
    利润
    0.08
    打印
    0.08
    ball
    0.08
     bizarre
    0.07
    奖金
    0.07
    _repeat
    0.07
     Mozart
    0.07
    Activations Density 0.152%

    No Known Activations