© 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. 646
    Prev
    Next
    INDEX
    Explanations

    after

    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
    arek
    -0.08
    ശ
    -0.08
     brute
    -0.07
     versa
    -0.07
    _copy
    -0.07
    journ
    -0.07
    _ids
    -0.07
    Fil
    -0.07
     provar
    -0.07
    assigned
    -0.07
    POSITIVE LOGITS
    账
    0.08
     образования
    0.08
    供
    0.08
     seedu
    0.08
    โ
    0.07
     indicating
    0.07
    "io
    0.07
     por
    0.07
     longstanding
    0.07
    ‌ده
    0.07
    Activations Density 0.002%

    No Known Activations