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. 52887
    Prev
    Next
    INDEX
    Explanations

    code, configurations

    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
     analyzed
    -0.08
     exploited
    -0.08
    otch
    -0.08
     percentual
    -0.08
     defeated
    -0.08
     lump
    -0.08
     nemo
    -0.08
     jedno
    -0.08
     espe
    -0.08
     oseb
    -0.08
    POSITIVE LOGITS
    stdint
    0.09
     union
    0.08
    ambient
    0.08
    Union
    0.07
     Titans
    0.07
     Ambient
    0.07
     conversar
    0.07
     ambiance
    0.07
     законодательства
    0.07
     serene
    0.07
    Activations Density 0.002%

    No Known Activations