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. 97970
    Prev
    Next
    INDEX
    Explanations

    say "Ey" words

    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
    elk
    -0.08
    Roster
    -0.08
     Forma
    -0.07
    SK
    -0.07
    edik
    -0.07
    ’am
    -0.07
    Forma
    -0.07
    wam
    -0.07
     matin
    -0.07
    132
    -0.07
    POSITIVE LOGITS
     qu
    0.08
     क्व
    0.08
     üstün
    0.08
    ovo
    0.08
    ivar
    0.08
     पक्ष
    0.08
     Qu
    0.08
    legenheit
    0.07
    레이
    0.07
    ugq
    0.07
    Activations Density 0.014%

    No Known Activations