© 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. 18295
    Prev
    Next
    INDEX
    Explanations

    最高

    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
     as
    -0.08
    Nz
    -0.08
    New
    -0.08
    డ
    -0.08
     via
    -0.07
     on
    -0.07
     );
↵
    -0.07
    Time
    -0.07
    ட
    -0.07
     nhớ
    -0.07
    POSITIVE LOGITS
     खू
    0.10
    掲載
    0.09
    represent
    0.09
     improperly
    0.09
     representar
    0.09
    positor
    0.09
     attractive
    0.09
     representan
    0.09
    feature
    0.09
     representa
    0.08
    Activations Density 0.000%

    No Known Activations