© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 97490
    Prev
    Next
    INDEX
    Explanations

    say "the ending -ology"

    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
    орат
    -0.09
    даться
    -0.09
     exemptions
    -0.09
    edores
    -0.08
     Curt
    -0.08
    драв
    -0.08
    orske
    -0.08
    braio
    -0.08
    няй
    -0.08
    ائص
    -0.08
    POSITIVE LOGITS
    opolitan
    0.23
    ology
    0.16
    ological
    0.16
    opolis
    0.13
    ogenesis
    0.13
    ography
    0.12
    ologies
    0.12
    ogram
    0.12
    ogenic
    0.12
    ochemistry
    0.12
    Activations Density 0.003%

    No Known Activations