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

    Neuronpedia

    APICircuit 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. 7-RESID-POST-AA
    6. 131002
    Prev
    Next
    INDEX
    Explanations

    Faraday

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lifting
    -0.07
     taxing
    -0.07
    ительной
    -0.07
    Dato
    -0.07
    ();
    ↵
    -0.07
    Closing
    -0.07
     Lisp
    -0.07
     נמ
    -0.07
    akor
    -0.07
     Verein
    -0.07
    POSITIVE LOGITS
     ज्ञान
    0.08
     knowledge
    0.08
     Knowledge
    0.07
     Dict
    0.07
    认为
    0.07
    tell
    0.07
     Solo
    0.07
     Valuable
    0.07
     Reliable
    0.07
     connaissance
    0.07
    Activations Density 0.001%

    No Known Activations