© 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. 23-RESID-POST-AA
    11. 51369
    Prev
    Next
    INDEX
    Explanations

    basketball plays

    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
    عل
    -0.09
     મે�
    -0.08
     danych
    -0.08
    ų
    -0.08
     récente
    -0.07
     dort
    -0.07
     डेटा
    -0.07
    」は
    -0.07
     Studien
    -0.07
    /m
    -0.07
    POSITIVE LOGITS
    DAC
    0.10
     pedag
    0.08
    dac
    0.08
     conditional
    0.08
    ADI
    0.08
    χή
    0.08
    Nearly
    0.07
    ACI
    0.07
     生命周期
    0.07
     DAC
    0.07
    Activations Density 0.001%

    No Known Activations