© 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. 99216
    Prev
    Next
    INDEX
    Explanations

    two-factor authentication

    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
     NOI
    -0.09
     nutrient
    -0.08
     receptive
    -0.07
     szer
    -0.07
     grievances
    -0.07
     tying
    -0.07
     bigint
    -0.07
     Rd
    -0.07
     weaken
    -0.07
     dollar
    -0.07
    POSITIVE LOGITS
    ASHION
    0.08
     أجل
    0.08
     встро
    0.08
    igrations
    0.08
    ented
    0.08
     إلكتر
    0.08
    _fu
    0.08
     Rochelle
    0.08
    denk
    0.08
     eingerichtet
    0.07
    Activations Density 0.002%

    No Known Activations