© 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. 75521
    Prev
    Next
    INDEX
    Explanations

    had

    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
    이어
    -0.08
    ilhar
    -0.08
     Stahl
    -0.08
     NAV
    -0.08
    .Mixed
    -0.08
     Baptist
    -0.08
     מידע
    -0.08
    isment
    -0.08
    ilerin
    -0.08
     lese
    -0.07
    POSITIVE LOGITS
    ెక్ట
    0.09
     shorter
    0.08
    0.07
     circumstances
    0.07
     longer
    0.07
     జన
    0.07
     alternatives
    0.07
    ynchron
    0.07
    perm
    0.07
     ubi
    0.07
    Activations Density 0.011%
    No Known Activations