© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 48250
    Prev
    Next
    INDEX
    Explanations

    761

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    spraak
    -0.09
    KR
    -0.08
     कपूर
    -0.08
     کشمیر
    -0.08
     హైదరాబాద్
    -0.08
     entièrement
    -0.08
     काठमाडौं
    -0.08
    ್ಕೆ
    -0.08
     כר
    -0.08
     KR
    -0.08
    POSITIVE LOGITS
    _t
    0.08
     Round
    0.07
    _T
    0.07
    .star
    0.07
     Unit
    0.07
    ās
    0.07
    _man
    0.07
    تق
    0.07
    905
    0.07
    T
    0.07
    Activations Density 0.000%

    No Known Activations