© 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. 8198
    Prev
    Next
    INDEX
    Explanations

    not

    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
     presumably
    -0.09
     reportedly
    -0.09
     apparently
    -0.09
     näiteks
    -0.09
     beispielsweise
    -0.09
     Rory
    -0.08
     notamment
    -0.08
     exempel
    -0.08
     Concrete
    -0.08
     aparentemente
    -0.08
    POSITIVE LOGITS
     mechan
    0.08
     الإلكترونية
    0.08
    _eta
    0.08
     unnecessary
    0.08
     relying
    0.07
    Eta
    0.07
     efficiency
    0.07
    Leaving
    0.07
     محدود
    0.07
     نک
    0.07
    Activations Density 0.025%

    No Known Activations