© 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. 11-RESID-POST-AA
    11. 8213
    Prev
    Next
    INDEX
    Explanations

    ai

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    처
    -0.08
     equival
    -0.08
    .solve
    -0.07
    앤
    -0.07
     venus
    -0.07
    ocal
    -0.07
     accreditation
    -0.07
    뜨
    -0.07
     Boll
    -0.07
    еге
    -0.07
    POSITIVE LOGITS
     Daten
    0.09
     tiny
    0.09
     miniature
    0.08
     Motorcycle
    0.08
     diesen
    0.08
     खु
    0.08
    Rtc
    0.08
    ित्व
    0.08
     Wohnzimmer
    0.08
     Faust
    0.08
    Activations Density 0.002%

    No Known Activations