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. 23-RESID-POST-AA
    6. 97094
    Prev
    Next
    INDEX
    Explanations

    c

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sink
    -0.08
     ನಿಧ
    -0.08
     seep
    -0.07
    DS
    -0.07
    嫩
    -0.07
     flinke
    -0.07
     spender
    -0.07
    .drawable
    -0.07
     Air
    -0.07
    OV
    -0.07
    POSITIVE LOGITS
    olais
    0.10
    -aut
    0.08
    eyond
    0.08
    onomies
    0.08
    otherap
    0.07
    -ọ
    0.07
    ifax
    0.07
    boys
    0.07
     fictional
    0.07
    istí
    0.07
    Activations Density 0.001%

    No Known Activations