© 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. 47974
    Prev
    Next
    INDEX
    Explanations

    1

    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
    .includes
    -0.09
     genetically
    -0.08
    _business
    -0.08
     إ
    -0.07
     Prayer
    -0.07
     sterke
    -0.07
    иву
    -0.07
    .astype
    -0.07
    iefer
    -0.07
     ases
    -0.07
    POSITIVE LOGITS
     fixes
    0.09
    -ek
    0.08
    зо
    0.08
    -sa
    0.08
    sek
    0.07
     fixing
    0.07
    -example
    0.07
     semester
    0.07
    պես
    0.07
     Eq
    0.07
    Activations Density 0.071%

    No Known Activations