© 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. 47889
    Prev
    Next
    INDEX
    Explanations

    Friends

    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
    ုပ်
    -0.08
    883
    -0.08
     prospective
    -0.07
     controlling
    -0.07
     cib
    -0.07
    Kit
    -0.07
    TO
    -0.07
     incident
    -0.07
     ações
    -0.07
    Incident
    -0.07
    POSITIVE LOGITS
     partout
    0.08
     calendario
    0.08
     contractions
    0.08
     contracted
    0.08
     келиш
    0.08
     NM
    0.08
     kalor
    0.08
     مهم
    0.08
     acquaintances
    0.08
     inol
    0.08
    Activations Density 0.002%

    No Known Activations