© 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. 12944
    Prev
    Next
    INDEX
    Explanations

    ORDER

    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
     Gw
    -0.07
     Hamas
    -0.07
    Talking
    -0.07
     resurf
    -0.07
    yas
    -0.07
    .topic
    -0.07
     gw
    -0.07
     Romantic
    -0.07
     secrets
    -0.07
     કો�
    -0.07
    POSITIVE LOGITS
    Alphabet
    0.08
    ni
    0.08
    pu
    0.07
     alphabet
    0.07
    NI
    0.07
     alph
    0.07
     Alphabet
    0.07
     cardinal
    0.07
    ANGUAGE
    0.07
     infinit
    0.07
    Activations Density 0.001%

    No Known Activations