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. 11578
    Prev
    Next
    INDEX
    Explanations

    code/logic outputs

    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
    .apply
    -0.08
     эфф
    -0.08
    (double
    -0.07
    .self
    -0.07
     Dinge
    -0.07
     integrating
    -0.07
     simpler
    -0.07
     parl
    -0.07
    .Nombre
    -0.07
     usable
    -0.07
    POSITIVE LOGITS
     ✓
    0.09
     xor
    0.08
    Abstract
    0.08
     ignite
    0.08
     afric
    0.08
    ,此
    0.07
     Abstract
    0.07
     усп
    0.07
    іс
    0.07
     moderate
    0.07
    Activations Density 0.045%

    No Known Activations