Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 112960
    Prev
    Next
    INDEX
    Explanations

    SQL SELECT statements

    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
    iameter
    -0.10
     Resin
    -0.09
    _threshold
    -0.08
     stärken
    -0.08
     مرسته
    -0.08
    pickle
    -0.08
    urethane
    -0.08
    磨
    -0.08
    _validator
    -0.08
    _thr
    -0.08
    POSITIVE LOGITS
     SELECT
    0.11
     (*)
    0.09
    SELECT
    0.09
     DISTINCT
    0.09
    (*)
    0.08
     projection
    0.08
     varchar
    0.08
     selective
    0.08
    FROM
    0.08
    มาย
    0.08
    Activations Density 0.007%

    No Known Activations