© 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. 644
    Prev
    Next
    INDEX
    Explanations

    Ambiguous reasoning scenarios

    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
     Lu
    -0.08
    ############################################################################
    -0.08
    #if
    -0.08
     제
    -0.07
     Không
    -0.07
    _requests
    -0.07
    .Servlet
    -0.07
    ----------------------------------------------------------------
    -0.07
     unfor
    -0.07
     reto
    -0.07
    POSITIVE LOGITS
    wab
    0.08
    Zend
    0.08
    cas
    0.07
     pertains
    0.07
    istri
    0.07
    pera
    0.07
     Damascus
    0.07
    Che
    0.07
     Cardiff
    0.07
     Bosnia
    0.07
    Activations Density 0.198%

    No Known Activations