© 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. 54897
    Prev
    Next
    INDEX
    Explanations

    compress

    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
    DET
    -0.08
    Det
    -0.08
     heartfelt
    -0.07
    Jed
    -0.07
    inem
    -0.07
     det
    -0.07
    look
    -0.07
     bleek
    -0.07
     Jed
    -0.07
     originale
    -0.07
    POSITIVE LOGITS
     collapsing
    0.09
     Eing
    0.09
     entering
    0.08
    örer
    0.08
    árs
    0.08
     colorectal
    0.08
     столк
    0.08
     тонн
    0.08
     Collapse
    0.08
     Aguil
    0.08
    Activations Density 0.002%

    No Known Activations