© 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. 19-RESID-POST-AA
    11. 102620
    Prev
    Next
    INDEX
    Explanations

    programming context

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     simples
    -0.08
    .•
    -0.08
    viders
    -0.08
    ­le
    -0.08
    аме
    -0.08
    álně
    -0.08
    .ALL
    -0.08
    .selector
    -0.08
     léir
    -0.08
    	Simple
    -0.08
    POSITIVE LOGITS
    -F
    0.08
    test
    0.08
    _F
    0.08
     टेस्ट
    0.08
    checkbox
    0.08
     checkbox
    0.07
    TEST
    0.07
    _REQUEST
    0.07
    dd
    0.07
    -week
    0.07
    Activations Density 0.000%

    No Known Activations