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. 131053
    Prev
    Next
    INDEX
    Explanations

    interface

    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
     Ai
    -0.12
     Ci
    -0.12
    Ai
    -0.11
    _ci
    -0.10
     Qi
    -0.10
     RCA
    -0.10
     Yi
    -0.10
     Cari
    -0.10
    dni
    -0.10
    usti
    -0.10
    POSITIVE LOGITS
     IM
    0.25
    IM
    0.25
     IS
    0.24
    IS
    0.24
     IF
    0.23
    IF
    0.22
    IC
    0.22
    .IM
    0.22
    (IM
    0.22
    ID
    0.21
    Activations Density 0.009%

    No Known Activations