© 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. 8096
    Prev
    Next
    INDEX
    Explanations

    enthusiast, lover

    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
     praça
    -0.08
     이후
    -0.08
     بق
    -0.08
     عن
    -0.08
    梁
    -0.08
     إطار
    -0.08
     drugo
    -0.07
     sitzen
    -0.07
    ql
    -0.07
     указан
    -0.07
    POSITIVE LOGITS
    人士
    0.10
     enthusiasts
    0.09
     approfond
    0.09
     keen
    0.08
     interesados
    0.08
     banget
    0.08
     discerning
    0.08
     enthusiast
    0.07
     Vereins
    0.07
     hobbies
    0.07
    Activations Density 0.034%

    No Known Activations