© 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. 6158
    Prev
    Next
    INDEX
    Explanations

    У

    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
    entee
    -0.09
     Dye
    -0.08
    -control
    -0.08
     строг
    -0.08
    opers
    -0.08
     отды
    -0.07
     inaugur
    -0.07
     отлич
    -0.07
    ್ಕ
    -0.07
     violently
    -0.07
    POSITIVE LOGITS
    AC
    0.08
    אנ
    0.08
    Ն
    0.08
    VERY
    0.08
    АК
    0.07
    �
    0.07
     påvir
    0.07
    inch
    0.07
    লীগ
    0.07
     AC
    0.07
    Activations Density 0.000%

    No Known Activations