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. 60943
    Prev
    Next
    INDEX
    Explanations

    commas and read

    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
    Apache
    -0.08
    apore
    -0.08
     stär
    -0.08
     Apache
    -0.07
    چه
    -0.07
    ιδ
    -0.07
     immortal
    -0.07
     (€
    -0.07
     appréci
    -0.07
    -0.07
    POSITIVE LOGITS
     lij
    0.08
     linewidth
    0.08
     ierr
    0.08
    Directive
    0.07
     неис
    0.07
     eql
    0.07
     Wy
    0.07
    asen
    0.07
     Mrs
    0.07
     plt
    0.07
    Activations Density 0.003%

    No Known Activations