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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 16513
    Prev
    Next
    INDEX
    Explanations

    imuth

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .instances
    -0.10
     nursing
    -0.08
    _instances
    -0.08
     instances
    -0.08
    .modules
    -0.08
    [_
    -0.08
    .singleton
    -0.07
    .INSTANCE
    -0.07
    “一
    -0.07
     tente
    -0.07
    POSITIVE LOGITS
    imuth
    0.10
    _angle
    0.10
     angle
    0.09
    قيب
    0.09
     clockwise
    0.09
    Angle
    0.08
     cosine
    0.08
    cklen
    0.08
     angles
    0.08
    Radians
    0.08
    Activations Density 0.002%

    No Known Activations