© 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. 45247
    Prev
    Next
    INDEX
    Explanations

    all

    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
     doux
    -0.09
    -|
    -0.08
     lấy
    -0.08
     traff
    -0.08
     soit
    -0.08
     Pleasure
    -0.08
     Praia
    -0.08
     Billing
    -0.07
     lingerie
    -0.07
     Trilogy
    -0.07
    POSITIVE LOGITS
    emoc
    0.08
     stewardship
    0.07
     potvr
    0.07
     bestätigen
    0.07
     eus
    0.07
     Ezek
    0.07
    Instantiate
    0.07
     edu
    0.07
    edic
    0.07
     administering
    0.07
    Activations Density 0.001%

    No Known Activations