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. 119172
    Prev
    Next
    INDEX
    Explanations

    car

    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
    Macros
    -0.08
     eh
    -0.08
    prises
    -0.08
     Barr
    -0.08
     abraço
    -0.08
    éments
    -0.07
    Barr
    -0.07
     introd
    -0.07
    iex
    -0.07
     geprägt
    -0.07
    POSITIVE LOGITS
    ’s
    0.09
     પાસે
    0.09
    さん
    0.08
    টির
    0.08
     initially
    0.08
     supposedly
    0.07
    \'
    0.07
     rijdt
    0.07
     coag
    0.07
     चले
    0.07
    Activations Density 0.054%

    No Known Activations