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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 78855
    Prev
    Next
    INDEX
    Explanations

    Sharp S (German)

    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
     snorkeling
    -0.09
    eel
    -0.08
    endid
    -0.08
     contraintes
    -0.08
    otok
    -0.08
     spéc
    -0.08
    _constraints
    -0.08
    PEc
    -0.08
     गेल
    -0.07
    enar
    -0.07
    POSITIVE LOGITS
     Von
    0.08
     Douglas
    0.07
     Samstag
    0.07
    .lookup
    0.07
    ันดับ
    0.07
     Wholesale
    0.07
     Newspaper
    0.07
    uppen
    0.07
     newline
    0.07
    0.07
    Activations Density 0.009%
    No Known Activations