© 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. 47978
    Prev
    Next
    INDEX
    Explanations

    Delia Owens and Marie Curie

    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
    -0.08
     py
    -0.08
    TE
    -0.08
     tequila
    -0.08
    CHA
    -0.08
    BAR
    -0.08
     percussion
    -0.07
    কল
    -0.07
    Cha
    -0.07
     TRA
    -0.07
    POSITIVE LOGITS
    abat
    0.08
    apur
    0.08
    apus
    0.07
     keeps
    0.07
     absorbs
    0.07
    abı
    0.07
    >equals
    0.07
     keeping
    0.07
    ಿಂಗ
    0.07
    inging
    0.07
    Activations Density 0.000%
    No Known Activations