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. 98112
    Prev
    Next
    INDEX
    Explanations

    say "с" 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
     least
    -0.08
     tinc
    -0.08
    least
    -0.08
    ic
    -0.08
    ENC
    -0.07
     transparente
    -0.07
    mins
    -0.07
    adra
    -0.07
     tabb
    -0.07
    aur
    -0.07
    POSITIVE LOGITS
     المنش
    0.10
    стройство
    0.09
     kayak
    0.08
    823
    0.08
    .rot
    0.08
    стройства
    0.08
    .organization
    0.08
    ождения
    0.08
    724
    0.08
    .rotation
    0.08
    Activations Density 0.000%

    No Known Activations