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. 98045
    Prev
    Next
    INDEX
    Explanations

    say "akes"

    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
    olella
    -0.08
    עלי
    -0.08
     Bergen
    -0.08
     mote
    -0.07
    iab
    -0.07
     Ellie
    -0.07
    .RED
    -0.07
    .Delete
    -0.07
     évoluer
    -0.07
     bakım
    -0.07
    POSITIVE LOGITS
     handshake
    0.12
     shook
    0.11
     shaking
    0.10
    shake
    0.09
    uffling
    0.09
    akes
    0.09
    uffles
    0.09
    uckles
    0.09
    ud
    0.09
    udd
    0.08
    Activations Density 0.000%

    No Known Activations