© 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. 23-RESID-POST-AA
    11. 6267
    Prev
    Next
    INDEX
    Explanations

    fantasy characters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _creator
    -0.08
     commenters
    -0.08
    老太
    -0.08
    ね
    -0.08
    _parent
    -0.08
     conversations
    -0.08
    _cli
    -0.08
     explanatory
    -0.08
     Mrs
    -0.08
    电影网站
    -0.08
    POSITIVE LOGITS
     prod
    0.11
     shin
    0.10
     wiel
    0.10
     chun
    0.10
     Field
    0.09
     fighter
    0.09
     Fields
    0.09
     operative
    0.09
     elever
    0.09
     élèves
    0.09
    Activations Density 0.028%

    No Known Activations