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. 90199
    Prev
    Next
    INDEX
    Explanations

    wise

    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
    iba
    -0.09
     Awake
    -0.08
    seer
    -0.08
    capt
    -0.08
     Агар
    -0.08
     NAS
    -0.08
     Thy
    -0.08
     Transformer
    -0.07
     Chase
    -0.07
     혹
    -0.07
    POSITIVE LOGITS
     palettes
    0.07
     pint
    0.07
     inks
    0.07
     conjug
    0.07
     midnight
    0.07
    .Fore
    0.07
     pal
    0.07
    Topo
    0.07
     Mehrheit
    0.07
    umulative
    0.07
    Activations Density 0.002%

    No Known Activations