© 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 EvalsExportsAPI 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. 50070
    Prev
    Next
    INDEX
    Explanations

    K

    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
    кої
    -0.09
    рач
    -0.08
    คนิค
    -0.08
    _GREEN
    -0.08
    tica
    -0.08
     терапии
    -0.08
    ILITY
    -0.08
    റി
    -0.08
    কৈ
    -0.08
    ថ
    -0.08
    POSITIVE LOGITS
    ’Es
    0.08
    '-
    0.08
    ijnt
    0.07
    oten
    0.07
    uele
    0.07
    rollen
    0.07
    'organ
    0.07
    omber
    0.07
     collateral
    0.07
    362
    0.07
    Activations Density 0.002%

    No Known Activations