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. 43699
    Prev
    Next
    INDEX
    Explanations

    commas

    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
     attentive
    -0.07
    Does
    -0.07
    Realm
    -0.07
     doorstep
    -0.07
     bina
    -0.07
    -N
    -0.07
     irresponsible
    -0.07
     ರೂ
    -0.07
    learn
    -0.07
     badge
    -0.07
    POSITIVE LOGITS
     Figura
    0.08
    skraft
    0.08
    most
    0.08
     фигур
    0.08
     вверх
    0.08
    kka
    0.08
     Figuren
    0.08
     kaj
    0.08
     сверху
    0.08
     Figure
    0.07
    Activations Density 0.050%

    No Known Activations