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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 19150
    Prev
    Next
    INDEX
    Explanations

    投

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    уков
    -0.08
    OOK
    -0.07
    崎
    -0.07
    OUS
    -0.07
    ibly
    -0.07
    cule
    -0.07
    κι
    -0.07
    ือง
    -0.07
    IBLE
    -0.07
    κυ
    -0.07
    POSITIVE LOGITS
    ölkerung
    0.10
    არდება
    0.10
    .screen
    0.10
    篮
    0.10
    ೃತ್ತ
    0.10
    ექტ
    0.10
    影
    0.09
    _images
    0.09
    matụ
    0.09
    imentos
    0.09
    Activations Density 0.001%

    No Known Activations