© 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. 91252
    Prev
    Next
    INDEX
    Explanations

    to

    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
     Minis
    -0.08
     vitae
    -0.08
    imali
    -0.07
     conservatives
    -0.07
     mc
    -0.07
    quo
    -0.07
     invasive
    -0.07
    ’appar
    -0.07
     conç
    -0.07
    trk
    -0.07
    POSITIVE LOGITS
    Beg
    0.08
    Stake
    0.08
    Study
    0.07
    study
    0.07
    Karen
    0.07
    say
    0.07
    Stephanie
    0.07
    aila
    0.07
    Adam
    0.07
     Margar
    0.07
    Activations Density 0.017%

    No Known Activations