© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 24627
    Prev
    Next
    INDEX
    Explanations

    physics principles

    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
    .high
    -0.08
    quest
    -0.08
    手
    -0.07
    afruit
    -0.07
     hal
    -0.07
    OOLEAN
    -0.07
     freiwill
    -0.07
     ụzọ
    -0.07
    .square
    -0.07
     सकारात्मक
    -0.07
    POSITIVE LOGITS
     laws
    0.10
     invari
    0.09
     Laws
    0.08
     intemp
    0.08
     одинаков
    0.08
     indifferent
    0.08
    laws
    0.08
     Ambient
    0.08
     कानून
    0.08
    _Il
    0.08
    Activations Density 0.003%

    No Known Activations