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. 23-RESID-POST-AA
    6. 98200
    Prev
    Next
    INDEX
    Explanations

    Foreign words

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     deri
    -0.08
     funcionar
    -0.08
     headed
    -0.08
     topp
    -0.08
    	Err
    -0.07
    entrale
    -0.07
    estones
    -0.07
    dynamic
    -0.07
     henn
    -0.07
    .Rem
    -0.07
    POSITIVE LOGITS
    uels
    0.09
    ibig
    0.08
    utz
    0.08
    acija
    0.08
    ations
    0.08
    -ons
    0.08
    utzer
    0.08
    uzz
    0.08
    issä
    0.08
    ATIONS
    0.08
    Activations Density 0.000%

    No Known Activations