© 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. 68193
    Prev
    Next
    INDEX
    Explanations

    small nature scene descriptions

    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
    -pressure
    -0.08
    coef
    -0.08
    vim
    -0.07
    -required
    -0.07
    -duty
    -0.07
     kern
    -0.07
    -mus
    -0.07
    арактер
    -0.07
    -get
    -0.07
     reps
    -0.07
    POSITIVE LOGITS
     secluded
    0.10
    溪
    0.09
     refuge
    0.08
     waterfalls
    0.08
     Mosque
    0.08
     roads
    0.08
     refugi
    0.08
    塘
    0.08
     Refuge
    0.08
     黄
    0.08
    Activations Density 0.015%

    No Known Activations