© 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. 50134
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    Badge
    -0.09
     игруш
    -0.09
     decomposition
    -0.09
     subgroup
    -0.08
    _categoria
    -0.08
     бактер
    -0.08
    VNode
    -0.08
     витам
    -0.08
    Svg
    -0.08
     toys
    -0.08
    POSITIVE LOGITS
     double
    0.19
     Times
    0.17
    	double
    0.17
     Double
    0.17
    double
    0.17
     doble
    0.16
    Calibri
    0.16
    -double
    0.15
    Double
    0.15
    .double
    0.15
    Activations Density 0.018%

    No Known Activations