© 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. 3-RESID-POST-AA
    11. 2515
    Prev
    Next
    INDEX
    Explanations

    exist

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nul
    -0.08
    <B
    -0.08
     solt
    -0.07
    ాలు
    -0.07
    ాలను
    -0.07
    adle
    -0.07
     संयुक्त
    -0.07
     explo
    -0.07
    డు
    -0.07
     gewähr
    -0.07
    POSITIVE LOGITS
    Lite
    0.08
    然
    0.07
    主
    0.07
    segu
    0.07
    แบบ
    0.07
    -lite
    0.07
     પાછળ
    0.07
     Editions
    0.07
     exaggerated
    0.07
     Fiction
    0.07
    Activations Density 0.011%

    No Known Activations