© 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. 47368
    Prev
    Next
    INDEX
    Explanations

    special characters

    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
     Mede
    -0.08
    -0.08
     xen
    -0.07
    irio
    -0.07
     Mull
    -0.07
     прот
    -0.07
     Vais
    -0.07
     grec
    -0.07
    ంటి
    -0.07
     Proc
    -0.07
    POSITIVE LOGITS
    because
    0.08
    (ext
    0.07
    ckt
    0.07
    iat
    0.07
    why
    0.07
     thereby
    0.07
     significativa
    0.07
    _best
    0.07
    jn
    0.07
    ਆ
    0.07
    Activations Density 0.010%
    No Known Activations