© 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. 237
    Prev
    Next
    INDEX
    Explanations

    German

    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
     orch
    -0.08
    ulating
    -0.08
     sanct
    -0.08
     tinted
    -0.07
     अश
    -0.07
     towers
    -0.07
    �
    -0.07
     qur
    -0.07
    华
    -0.07
     tucked
    -0.07
    POSITIVE LOGITS
    font
    0.08
    means
    0.08
    emotion
    0.08
    -Z
    0.08
    dem
    0.08
    _OCC
    0.08
    fam
    0.08
    gam
    0.08
    Oms
    0.08
    Means
    0.07
    Activations Density 0.001%

    No Known Activations