© 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. 6202
    Prev
    Next
    INDEX
    Explanations

    say "d" word

    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
     separator
    -0.10
    delimiter
    -0.10
     delimiter
    -0.10
    _SEPARATOR
    -0.10
    separator
    -0.09
     Separation
    -0.09
    Delimiter
    -0.09
     slash
    -0.09
     Separ
    -0.09
     Separator
    -0.09
    POSITIVE LOGITS
     em
    0.14
     —
    0.11
     longer
    0.11
    /em
    0.11
    ’em
    0.11
    'em
    0.10
    -em
    0.10
    —
    0.10
    (em
    0.10
     d
    0.10
    Activations Density 0.005%

    No Known Activations