© 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. 78283
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    ətin
    -0.08
     trab
    -0.07
    েট
    -0.07
    ox
    -0.07
     realist
    -0.07
    (Migration
    -0.07
    Vip
    -0.07
    escription
    -0.07
    .now
    -0.07
     vot
    -0.07
    POSITIVE LOGITS
     idi
    0.08
     childs
    0.08
     чак
    0.08
    0.08
     identities
    0.08
     transforms
    0.08
     Courtesy
    0.07
     usado
    0.07
     Used
    0.07
     Wisdom
    0.07
    Activations Density 0.034%
    No Known Activations