Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 58653
    Prev
    Next
    INDEX
    Explanations

    hedral

    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
    .googleapis
    -0.09
    volume
    -0.08
    ízo
    -0.08
    meldung
    -0.08
     Weston
    -0.08
     Bellevue
    -0.08
     volume
    -0.08
     <--
    -0.08
    heit
    -0.08
    importance
    -0.08
    POSITIVE LOGITS
     sezon
    0.09
    合同
    0.08
    ੱਖ
    0.08
     раск
    0.08
     аксесс
    0.08
    ნა
    0.08
     reflections
    0.08
     oppos
    0.08
     clockwise
    0.07
    CCESS
    0.07
    Activations Density 0.003%

    No Known Activations