Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 43489
    Prev
    Next
    INDEX
    Explanations

    state

    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
    试看
    -0.08
     lẹ
    -0.08
     Whites
    -0.08
     board
    -0.08
     Trademark
    -0.07
     ped
    -0.07
    licate
    -0.07
     Jew
    -0.07
     rapidez
    -0.07
    赛车
    -0.07
    POSITIVE LOGITS
     resets
    0.10
    /reset
    0.09
     nearing
    0.08
    Reset
    0.08
    (reset
    0.08
    uiste
    0.08
     poorly
    0.07
     resetting
    0.07
    0.07
    .reset
    0.07
    Activations Density 0.001%

    No Known Activations