© 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. 65414
    Prev
    Next
    INDEX
    Explanations

    liking

    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
    盗
    -0.08
    cial
    -0.08
     Guerr
    -0.07
    ోగ
    -0.07
    licos
    -0.07
    ylim
    -0.07
    Gang
    -0.07
    �
    -0.07
    -L
    -0.07
    ర్ల
    -0.07
    POSITIVE LOGITS
     lat
    0.08
     прих
    0.08
     unh
    0.08
     presumed
    0.07
     submiss
    0.07
     jurisdictions
    0.07
     kegiatan
    0.07
     pá
    0.07
    lat
    0.07
     eco
    0.07
    Activations Density 0.008%

    No Known Activations