Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 48340
    Prev
    Next
    INDEX
    Explanations

    say "atics"

    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
    ian
    -0.09
    rawn
    -0.08
    folio
    -0.08
    _por
    -0.08
    ual
    -0.08
     por
    -0.08
    continental
    -0.08
    owi
    -0.08
     Modal
    -0.08
    rcode
    -0.07
    POSITIVE LOGITS
    atics
    0.15
    atherapy
    0.14
    atiques
    0.12
    áticos
    0.10
     arom
    0.10
     herbs
    0.09
    ather
    0.09
     spices
    0.09
    atique
    0.09
    áticas
    0.09
    Activations Density 0.001%

    No Known Activations