Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 19095
    Prev
    Next
    INDEX
    Explanations

    technical or configuration context

    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
     BIOS
    -0.07
    у
    -0.07
     gradual
    -0.07
    ованный
    -0.07
    улу
    -0.07
     positively
    -0.07
    -0.07
     eternal
    -0.07
     cán
    -0.07
    Prere
    -0.06
    POSITIVE LOGITS
     tego
    0.10
    (which
    0.09
     vaiht
    0.09
     speziell
    0.08
     tuj
    0.08
    seven
    0.08
     miatt
    0.08
     eigh
    0.08
     sinds
    0.08
     schuld
    0.08
    Activations Density 0.000%

    No Known Activations