© 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. 11-RESID-POST-AA
    11. 75588
    Prev
    Next
    INDEX
    Explanations

    circle geometry

    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
     Hos
    -0.08
    _income
    -0.08
    _lineno
    -0.08
    ે�
    -0.08
    Hos
    -0.08
    세
    -0.07
     telefoni
    -0.07
    項
    -0.07
     maternal
    -0.07
    寄
    -0.07
    POSITIVE LOGITS
     radians
    0.14
     angular
    0.09
    Radians
    0.09
    RAW
    0.09
    .angle
    0.09
    /span
    0.08
    Angle
    0.08
     Angle
    0.08
    -angle
    0.08
     span
    0.08
    Activations Density 0.019%

    No Known Activations