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. 12269
    Prev
    Next
    INDEX
    Explanations

    Nobel

    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
     prédio
    -0.08
     એવી
    -0.07
    mæ
    -0.07
     Maroc
    -0.07
     campground
    -0.07
    ево
    -0.07
    ;">
    -0.07
    mico
    -0.07
     Sanders
    -0.07
     parcel
    -0.07
    POSITIVE LOGITS
     Nobel
    0.11
     platinum
    0.09
     jaune
    0.08
     atribu
    0.08
    [N
    0.08
    -family
    0.08
     сия
    0.08
    ियम
    0.08
     peaceful
    0.07
     laure
    0.07
    Activations Density 0.003%

    No Known Activations