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. 130954
    Prev
    Next
    INDEX
    Explanations

    say "the ending -imes"

    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
    áž
    -0.09
    龙虎
    -0.08
    al
    -0.08
    的天堂
    -0.08
    cluding
    -0.08
    ändigen
    -0.08
    famil
    -0.08
     revisión
    -0.08
     uchel
    -0.08
     العالي
    -0.08
    POSITIVE LOGITS
    imes
    0.20
    imest
    0.12
    ime
    0.11
    ensor
    0.09
    omb
    0.08
    IMP
    0.08
    imap
    0.08
     Tensor
    0.08
    ombs
    0.08
    imt
    0.08
    Activations Density 0.000%

    No Known Activations