© 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. 1326
    Prev
    Next
    INDEX
    Explanations

    )

    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
    Disc
    -0.08
     minn
    -0.07
    .disk
    -0.07
     Bots
    -0.07
     **/↵↵
    -0.07
    _datetime
    -0.07
    研
    -0.07
     Disc
    -0.07
     cérémonie
    -0.07
    -disc
    -0.07
    POSITIVE LOGITS
    <|reserved_200016|>
    0.09
    <|endoftext|>
    0.08
     sweat
    0.08
     overcoming
    0.07
     заключается
    0.07
     risque
    0.07
     위험
    0.07
    난
    0.07
    مد
    0.07
     ylim
    0.07
    Activations Density 0.047%

    No Known Activations