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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 90164
    Prev
    Next
    INDEX
    Explanations

    directed graphs

    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
    ിച്ച്
    -0.08
    待
    -0.07
     insured
    -0.07
    lsen
    -0.07
     matériels
    -0.07
    houd
    -0.07
     collided
    -0.07
    ln
    -0.07
     మేర
    -0.07
     clam
    -0.07
    POSITIVE LOGITS
     rotor
    0.10
     Rotor
    0.10
    Rotor
    0.09
    angular
    0.08
     arrows
    0.08
    箭
    0.08
    Oval
    0.08
     arrow
    0.08
     вет
    0.08
     weaker
    0.08
    Activations Density 0.006%

    No Known Activations