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. 130918
    Prev
    Next
    INDEX
    Explanations

    unfor

    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
    肥
    -0.09
     स्ल
    -0.08
     arranc
    -0.08
    erde
    -0.08
    armik
    -0.08
     kreative
    -0.08
    ärmen
    -0.08
     информацию
    -0.07
    ertjes
    -0.07
     dial
    -0.07
    POSITIVE LOGITS
    giving
    0.17
    given
    0.13
    giver
    0.12
    giv
    0.11
    unately
    0.11
    give
    0.10
     giving
    0.10
    unate
    0.10
    给予
    0.09
    seen
    0.09
    Activations Density 0.001%

    No Known Activations