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. 11-RESID-POST-AA
    6. 53939
    Prev
    Next
    INDEX
    Explanations

    the

    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
     dokon
    -0.09
     milag
    -0.08
     crow
    -0.08
     Sac
    -0.08
     Федера
    -0.08
     Apache
    -0.08
    .Mar
    -0.08
     mirac
    -0.08
     glaube
    -0.08
     foule
    -0.08
    POSITIVE LOGITS
     hochwertigen
    0.08
     witty
    0.08
    Upper
    0.08
     hoogwaardige
    0.07
    haut
    0.07
     memorize
    0.07
     reasonably
    0.07
    Detailed
    0.07
    ksam
    0.07
     nuc
    0.07
    Activations Density 0.023%

    No Known Activations