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. 12436
    Prev
    Next
    INDEX
    Explanations

    RUP

    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
     directamente
    -0.09
     напрямую
    -0.09
    ాకు
    -0.08
     diretamente
    -0.08
     Radeon
    -0.08
     직접
    -0.07
     непосред
    -0.07
     וח
    -0.07
     непосредственно
    -0.07
     unmittel
    -0.07
    POSITIVE LOGITS
     militar
    0.08
    Macro
    0.08
     अपन
    0.08
    ledning
    0.08
    Guid
    0.08
    ေတာ္
    0.07
    Digit
    0.07
    _default
    0.07
    itlement
    0.07
    Voilà
    0.07
    Activations Density 0.001%

    No Known Activations