© 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. 65440
    Prev
    Next
    INDEX
    Explanations

    steve jobs quote

    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
     será
    -0.09
     fich
    -0.07
     growing
    -0.07
    ussu
    -0.07
     sera
    -0.07
    াণ
    -0.07
     iss
    -0.07
     seront
    -0.07
     bool
    -0.07
     flexibil
    -0.07
    POSITIVE LOGITS
     elk
    0.08
    Holy
    0.08
    _magic
    0.08
     Majority
    0.08
     murderous
    0.08
    mah
    0.08
    lege
    0.07
     הגדול
    0.07
    unsafe
    0.07
     Himalayan
    0.07
    Activations Density 0.000%

    No Known Activations