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. 98676
    Prev
    Next
    INDEX
    Explanations

    say "ines"

    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
    	core
    -0.09
    েট
    -0.09
    ोड
    -0.09
    ET
    -0.08
    	DECLARE
    -0.08
    ెట్
    -0.08
    ेट
    -0.08
     fiscale
    -0.08
     tribal
    -0.08
    core
    -0.08
    POSITIVE LOGITS
    ines
    0.11
    inth
    0.11
    INES
    0.10
    ine
    0.10
    inete
    0.10
    in
    0.09
     ninete
    0.09
    ueve
    0.09
    inee
    0.09
    inees
    0.09
    Activations Density 0.004%

    No Known Activations