© 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. 96681
    Prev
    Next
    INDEX
    Explanations

    finding words/letter combinations

    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
    ാത്ത
    -0.09
    ാനം
    -0.09
    альная
    -0.08
    圆
    -0.08
    arning
    -0.07
    āl
    -0.07
     quiet
    -0.07
    /about
    -0.07
    ện
    -0.07
    асс
    -0.07
    POSITIVE LOGITS
    legs
    0.10
    filepath
    0.09
    jack
    0.09
    so
    0.09
    css
    0.08
    NODE
    0.08
    caps
    0.08
    widgets
    0.08
     filepath
    0.08
    Carl
    0.08
    Activations Density 0.003%

    No Known Activations