© 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. 500
    Prev
    Next
    INDEX
    Explanations

    attribution of behavior

    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
     freezer
    -0.08
     ounce
    -0.08
     handgun
    -0.08
     templ
    -0.08
     beau
    -0.07
    tsa
    -0.07
    31
    -0.07
    922
    -0.07
     secon
    -0.07
    tables
    -0.07
    POSITIVE LOGITS
     privados
    0.09
     motors
    0.08
     वि�
    0.08
     실패
    0.08
    Mocks
    0.08
     निजी
    0.08
    ailure
    0.08
    Witness
    0.08
     quieran
    0.07
     Motors
    0.07
    Activations Density 0.003%

    No Known Activations