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. 55884
    Prev
    Next
    INDEX
    Explanations

    at

    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
     વિસ્તાર
    -0.08
    _AP
    -0.07
    .props
    -0.07
    sqrt
    -0.07
     mother
    -0.07
    SK
    -0.07
     procl
    -0.07
    (er
    -0.07
     appliance
    -0.07
    Mother
    -0.07
    POSITIVE LOGITS
    dogs
    0.09
     Johan
    0.08
     Trips
    0.08
    .have
    0.08
     Biel
    0.08
     fishes
    0.08
     MDB
    0.07
     MGA
    0.07
     nineteen
    0.07
     подходят
    0.07
    Activations Density 0.000%

    No Known Activations