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. 112821
    Prev
    Next
    INDEX
    Explanations

    sensory

    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
    óvel
    -0.08
    xxx
    -0.07
    Pont
    -0.07
    raisal
    -0.07
    Viz
    -0.07
    Arte
    -0.07
    Conc
    -0.07
    Chat
    -0.07
    Photon
    -0.07
    viz
    -0.07
    POSITIVE LOGITS
    息
    0.08
     itching
    0.08
    信息
    0.08
    味
    0.08
     scents
    0.08
    声音
    0.08
     informacji
    0.08
     scent
    0.08
     정보를
    0.08
     impressions
    0.08
    Activations Density 0.003%

    No Known Activations