© 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. 11-RESID-POST-AA
    11. 108778
    Prev
    Next
    INDEX
    Explanations

    a and punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     barter
    -0.10
    .xlsx
    -0.09
     Semester
    -0.09
    	ON
    -0.08
     necesitar
    -0.08
     Neces
    -0.08
     RETURN
    -0.08
     الخيار
    -0.08
     Factors
    -0.08
     Cen
    -0.08
    POSITIVE LOGITS
     allegations
    0.10
     criticism
    0.10
     accusations
    0.10
     accus
    0.10
     accused
    0.10
     criticizing
    0.09
     LGBTQ
    0.09
     accusing
    0.09
     disrespect
    0.09
     alleging
    0.09
    Activations Density 0.096%

    No Known Activations