© 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. 6219
    Prev
    Next
    INDEX
    Explanations

    say "own"

    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
     sigo
    -0.08
     چار
    -0.08
    快捷
    -0.08
    гони
    -0.08
    ગી
    -0.08
    彻
    -0.08
     estre
    -0.08
    і
    -0.07
     ആശ
    -0.07
     editable
    -0.07
    POSITIVE LOGITS
    own
    0.15
    OWN
    0.08
     facilities
    0.08
    cap
    0.08
    -maint
    0.07
    owns
    0.07
    vl
    0.07
     menyebabkan
    0.07
    elt
    0.07
    field
    0.07
    Activations Density 0.000%

    No Known Activations