© 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. 11-RESID-POST-AA
    11. 110507
    Prev
    Next
    INDEX
    Explanations

    any

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tiếng
    -0.08
    ploader
    -0.07
    ={{↵
    -0.07
    ={{
    -0.07
     trakt
    -0.07
    �क
    -0.07
    .define
    -0.07
    Given
    -0.07
     भेज
    -0.07
     Playback
    -0.07
    POSITIVE LOGITS
     allgemein
    0.12
     generell
    0.09
     ANY
    0.09
     geldt
    0.09
     irrespective
    0.09
     Anyway
    0.09
    'importe
    0.08
     Allgemeinen
    0.08
    ，包括
    0.08
    —including
    0.08
    Activations Density 0.119%

    No Known Activations