© 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. 65426
    Prev
    Next
    INDEX
    Explanations

    Code errors

    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
    gradu
    -0.09
     Reveal
    -0.08
     FLOOR
    -0.08
    allon
    -0.08
     Genres
    -0.07
     większo
    -0.07
    Gradu
    -0.07
     kategori
    -0.07
     sudoku
    -0.07
     dissolve
    -0.07
    POSITIVE LOGITS
    ાઓ
    0.08
    561
    0.08
    _needed
    0.08
    544
    0.07
    ાના
    0.07
    0.07
    Needed
    0.07
     Glue
    0.07
    ция
    0.07
    541
    0.07
    Activations Density 0.011%
    No Known Activations