© 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. 5837
    Prev
    Next
    INDEX
    Explanations

    /T

    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
     Aluminium
    -0.10
     Alabama
    -0.09
    rolling
    -0.09
    rolled
    -0.09
     האל
    -0.08
    턴
    -0.08
     öld
    -0.08
     Aluminum
    -0.08
    組
    -0.08
    plings
    -0.08
    POSITIVE LOGITS
    ik
    0.15
    iktok
    0.12
    IK
    0.11
    ик
    0.11
    iknya
    0.10
    Tik
    0.10
    X
    0.09
     Tik
    0.09
    amano
    0.08
    ikl
    0.08
    Activations Density 0.000%

    No Known Activations