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. 59245
    Prev
    Next
    INDEX
    Explanations

    orders and subscriptions

    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
    inceton
    -0.08
    rev
    -0.07
    MQ
    -0.07
     trọng
    -0.07
    域
    -0.07
     duc
    -0.07
    irie
    -0.07
    ․
    -0.07
    arn
    -0.07
    ্রে
    -0.06
    POSITIVE LOGITS
     snabbt
    0.08
    ominations
    0.08
     свар
    0.08
     sg
    0.07
     crystals
    0.07
     Hatch
    0.07
     полез
    0.07
    setzungen
    0.07
    enarios
    0.07
     быстро
    0.07
    Activations Density 0.892%

    No Known Activations