© 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. 6173
    Prev
    Next
    INDEX
    Explanations

    h

    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
    gist
    -0.08
     något
    -0.08
    "profile
    -0.07
    gja
    -0.07
     təs
    -0.07
     Lorsque
    -0.07
     address
    -0.07
     تحدث
    -0.07
     supporting
    -0.07
    POSITIVE LOGITS
    ilah
    0.08
    'univers
    0.08
    ungan
    0.08
     paro
    0.08
     parab
    0.08
    ian
    0.08
    രിച്ചു
    0.08
    łość
    0.08
     disciples
    0.08
    解析
    0.07
    Activations Density 0.000%

    No Known Activations