© 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. 3-RESID-POST-AA
    11. 12795
    Prev
    Next
    INDEX
    Explanations

    format

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     сталки
    -0.08
     прив
    -0.08
    priv
    -0.08
     compens
    -0.08
    _since
    -0.08
     resur
    -0.08
     Crab
    -0.08
     ambient
    -0.07
     sonic
    -0.07
    Ambient
    -0.07
    POSITIVE LOGITS
    ulario
    0.08
    ters
    0.07
    667
    0.07
     divul
    0.07
     lei
    0.07
     Ba
    0.07
     don
    0.07
    �
    0.07
     sandals
    0.07
     Tai
    0.07
    Activations Density 0.018%

    No Known Activations