© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 11-RESID-POST-AA
    11. 129286
    Prev
    Next
    INDEX
    Explanations

    to

    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
     attraktive
    -0.08
     акы
    -0.08
     darah
    -0.08
    ‌కు
    -0.07
     toqq
    -0.07
     krev
    -0.07
     Dummy
    -0.07
     ο
    -0.07
     outfits
    -0.07
     iniss
    -0.07
    POSITIVE LOGITS
    <|endoftext|>
    0.09
    <|reserved_200016|>
    0.08
    leted
    0.07
    Yaml
    0.07
    oubted
    0.07
    abili
    0.07
    (UPDATED
    0.07
    paren
    0.07
    _OPTION
    0.07
     dessas
    0.07
    Activations Density 0.897%

    No Known Activations