© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 99246
    Prev
    Next
    INDEX
    Explanations

    bingo cards

    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
     blog
    -0.08
     lw
    -0.08
     symptoms
    -0.08
     succumb
    -0.08
     (^
    -0.07
     cures
    -0.07
    áns
    -0.07
     ziekenhuis
    -0.07
     homemade
    -0.07
    (person
    -0.07
    POSITIVE LOGITS
    Columns
    0.10
     coluna
    0.10
     columnas
    0.10
     columna
    0.09
    .columns
    0.09
     colonne
    0.09
    .column
    0.09
    Column
    0.09
    _columns
    0.09
    _partition
    0.08
    Activations Density 0.002%

    No Known Activations