© 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. 23-RESID-POST-AA
    11. 6255
    Prev
    Next
    INDEX
    Explanations

    say ".iter"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     хв
    -0.08
    -0.07
    Mixer
    -0.07
    ട്ടി
    -0.07
     ceremonial
    -0.07
    ان
    -0.07
     termin
    -0.07
    Church
    -0.07
     Church
    -0.07
    TRAN
    -0.07
    POSITIVE LOGITS
    odal
    0.08
    órdoba
    0.08
     vije
    0.08
     gen
    0.08
     collega
    0.08
     окно
    0.08
    žev
    0.08
    idr
    0.08
    Ổ
    0.08
     wnd
    0.08
    Activations Density 0.001%
    No Known Activations