© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 94505
    Prev
    Next
    INDEX
    Explanations

    puzzle solving

    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
     വര
    -0.08
    reasonable
    -0.07
     Seems
    -0.07
     definitely
    -0.07
    겠습니다
    -0.07
    gunaan
    -0.07
     reasonable
    -0.07
     Lange
    -0.07
     although
    -0.07
    라고
    -0.07
    POSITIVE LOGITS
     metaphor
    0.11
     cipher
    0.10
     parody
    0.10
    谜
    0.10
     Emoji
    0.10
     وو
    0.09
     figur
    0.09
     Pokémon
    0.09
     játék
    0.09
     Cipher
    0.09
    Activations Density 0.057%

    No Known Activations