© 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. 65364
    Prev
    Next
    INDEX
    Explanations

    Midjourney prompts

    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
    _^
    -0.08
    _Static
    -0.08
    649
    -0.08
    _Save
    -0.07
    -lived
    -0.07
    ੱ
    -0.07
    ubble
    -0.07
    .),
    -0.07
    .^
    -0.07
    breng
    -0.07
    POSITIVE LOGITS
     Demonstr
    0.10
     exemplos
    0.08
     Beispiele
    0.08
     illustrative
    0.08
     volonté
    0.08
     Kais
    0.08
     અગાઉ
    0.08
     Benchmark
    0.08
     frontera
    0.08
     શરૂ
    0.08
    Activations Density 0.003%

    No Known Activations