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. 97984
    Prev
    Next
    INDEX
    Explanations

    say "assion"

    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
    criterion
    -0.09
    romatic
    -0.09
     خلا
    -0.08
     criterion
    -0.08
     keessaa
    -0.08
     Κ
    -0.08
    linary
    -0.08
    ita
    -0.08
     çıktı
    -0.08
    iliga
    -0.07
    POSITIVE LOGITS
    assion
    0.11
    banken
    0.08
    bank
    0.08
    garten
    0.07
    g
    0.07
     forgiveness
    0.07
     maps
    0.07
     intentionally
    0.07
     banking
    0.07
    ance
    0.07
    Activations Density 0.001%

    No Known Activations