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. 98257
    Prev
    Next
    INDEX
    Explanations

    "ch"

    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
     bunga
    -0.08
    vald
    -0.08
     taraf
    -0.07
    adau
    -0.07
     doğr
    -0.07
     jaringan
    -0.07
    ī
    -0.07
     sht
    -0.07
    校
    -0.07
     quartiers
    -0.07
    POSITIVE LOGITS
    Ch
    0.12
     Ch
    0.12
     ch
    0.11
    _ch
    0.11
    ch
    0.11
    .Ch
    0.10
    _CH
    0.10
    _Ch
    0.10
    (ch
    0.10
    ,ch
    0.09
    Activations Density 0.022%

    No Known Activations