© 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. 7-RESID-POST-AA
    11. 1287
    Prev
    Next
    INDEX
    Explanations

    database schema changes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     развлеч
    -0.08
    층
    -0.08
    য়
    -0.08
     archive
    -0.07
    -0.07
    lein
    -0.07
     actors
    -0.07
     ub
    -0.07
    coder
    -0.07
     που
    -0.07
    POSITIVE LOGITS
    presa
    0.09
     Wichita
    0.08
     Turner
    0.08
     COLUMN
    0.08
    CW
    0.08
    Henry
    0.08
     CV
    0.08
     grd
    0.07
     Ester
    0.07
    CV
    0.07
    Activations Density 0.001%
    No Known Activations