© 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. 7-RESID-POST-AA
    11. 1464
    Prev
    Next
    INDEX
    Explanations

    konnte/konnten

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lan
    -0.08
    Lect
    -0.07
    lav
    -0.07
    lun
    -0.07
     bask
    -0.07
    lex
    -0.07
     Zheng
    -0.07
    樂
    -0.07
    旺
    -0.07
    tour
    -0.07
    POSITIVE LOGITS
     Consent
    0.08
     SIS
    0.07
    ’t
    0.07
     Twin
    0.07
     mér
    0.07
     hardly
    0.07
    FAC
    0.07
     Proven
    0.07
     exceedingly
    0.07
     Mah
    0.07
    Activations Density 0.006%

    No Known Activations