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. 11-RESID-POST-AA
    6. 113086
    Prev
    Next
    INDEX
    Explanations

    Russian

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -0.08
     financially
    -0.08
    plings
    -0.07
     locals
    -0.07
    में
    -0.07
     adaptive
    -0.07
    서는
    -0.07
     hereditary
    -0.07
    هو
    -0.07
    (il
    -0.07
    POSITIVE LOGITS
     Machinery
    0.08
     machinery
    0.08
    Mach
    0.08
    Make
    0.08
    _timestamp
    0.08
     กรุ
    0.08
     מקום
    0.08
     inté
    0.08
     Make
    0.08
     בלבד
    0.07
    Activations Density 0.017%

    No Known Activations