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. 234
    Prev
    Next
    INDEX
    Explanations

    Geological faults/earthquakes

    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
    chemy
    -0.08
     competitions
    -0.08
    íc
    -0.08
     Eyes
    -0.08
     cheese
    -0.08
     compiler
    -0.07
     lige
    -0.07
     vowel
    -0.07
     sond
    -0.07
    ॉय
    -0.07
    POSITIVE LOGITS
     noirs
    0.09
    /thumb
    0.08
    .Shared
    0.08
    cuento
    0.08
    Rot
    0.08
     negros
    0.08
     ход
    0.08
    besar
    0.08
    .Description
    0.08
     mandib
    0.08
    Activations Density 0.003%

    No Known Activations