Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 45055
    Prev
    Next
    INDEX
    Explanations

    hypothesis

    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
     Rioja
    -0.09
    Lessons
    -0.09
     gravy
    -0.09
    规律
    -0.08
    wyn
    -0.08
     lessons
    -0.08
     Luck
    -0.08
    -Sp
    -0.08
    outil
    -0.08
     glycol
    -0.08
    POSITIVE LOGITS
     formul
    0.09
     lautet
    0.09
     violated
    0.08
     formulate
    0.08
     Uncomment
    0.08
     техничес
    0.08
     vred
    0.08
     violation
    0.08
     Cardinal
    0.08
     bibliotek
    0.08
    Activations Density 0.003%

    No Known Activations