© 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. 23-RESID-POST-AA
    11. 48533
    Prev
    Next
    INDEX
    Explanations

    sqlalchemy

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Killed
    -0.08
    atora
    -0.07
    ledning
    -0.07
    Novel
    -0.07
    dorf
    -0.07
    Shoot
    -0.07
    Cult
    -0.07
    egree
    -0.07
    Hb
    -0.07
    Ys
    -0.07
    POSITIVE LOGITS
    .engine
    0.15
     engine
    0.13
    _engine
    0.12
    (engine
    0.11
    .orm
    0.11
    	engine
    0.11
    .ext
    0.11
    _ENGINE
    0.11
     engines
    0.10
    .create
    0.10
    Activations Density 0.002%

    No Known Activations