© 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. 26447
    Prev
    Next
    INDEX
    Explanations

    hexadecimal code

    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
     slogans
    -0.08
     slogan
    -0.08
     stod
    -0.08
    _campaign
    -0.08
    创造
    -0.08
     affection
    -0.08
    eree
    -0.07
     bun
    -0.07
     Concord
    -0.07
     disciplines
    -0.07
    POSITIVE LOGITS
     DWORD
    0.08
     BIOS
    0.08
     writable
    0.08
     carbide
    0.08
     encoding
    0.08
     malloc
    0.08
    0.08
     бай
    0.08
     sane
    0.07
     Ansatz
    0.07
    Activations Density 0.003%
    No Known Activations