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. 15-RESID-POST-AA
    6. 120
    Prev
    Next
    INDEX
    Explanations

    Mathematical arguments/functions

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     മെ
    -0.07
    ന്ന
    -0.07
    /C
    -0.07
    _crc
    -0.07
    5
    -0.07
    -0.07
     hollow
    -0.07
    Forever
    -0.07
     (
    -0.07
    **
    -0.07
    POSITIVE LOGITS
     liig
    0.11
     radians
    0.11
     angle
    0.10
     éché
    0.10
     notran
    0.09
     ministre
    0.09
     tiba
    0.09
     Angle
    0.09
    угаца
    0.09
     raakt
    0.09
    Activations Density 0.016%

    No Known Activations