Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 74333
    Prev
    Next
    INDEX
    Explanations

    black

    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
     SAFE
    -0.07
     describing
    -0.07
     complac
    -0.07
     growing
    -0.07
     experimentar
    -0.07
     Spe
    -0.07
     insecure
    -0.07
    ++,
    -0.07
     Stable
    -0.07
    SAFE
    -0.07
    POSITIVE LOGITS
     schwarze
    0.12
    黑
    0.12
     黑
    0.11
     preto
    0.11
     schwarzen
    0.11
    .black
    0.10
     black
    0.10
     mør
    0.10
     noire
    0.10
     negros
    0.10
    Activations Density 0.017%

    No Known Activations