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. 76448
    Prev
    Next
    INDEX
    Explanations

    repeated experiments and statistics

    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
    iram
    -0.09
     protr
    -0.09
     olup
    -0.08
    .Val
    -0.08
     HS
    -0.08
    _hd
    -0.08
    Vertices
    -0.08
     carbohydrates
    -0.08
    keletal
    -0.07
    Elevation
    -0.07
    POSITIVE LOGITS
     repetitions
    0.11
     repeatedly
    0.10
     batches
    0.10
     trials
    0.10
     repeated
    0.10
     반복
    0.10
    _trials
    0.10
    _runs
    0.10
     recordings
    0.10
     ಬಾರಿ
    0.10
    Activations Density 0.023%

    No Known Activations