© 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. 19-RESID-POST-AA
    11. 103067
    Prev
    Next
    INDEX
    Explanations

    data

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     problem
    -0.07
     hinter
    -0.07
     Somewhere
    -0.07
     etc
    -0.07
     '-
    -0.07
     lehen
    -0.07
     
    -0.07
     Suitable
    -0.07
    ▄▄
    -0.07
     Above
    -0.07
    POSITIVE LOGITS
    (){↵
    0.16
    (){
    0.16
    (){↵↵
    0.14
    (){}↵
    0.14
    =function
    0.13
    ()
    0.13
    (){
↵
    0.13
    (){↵//
    0.12
    ()`
    0.12
    (_,
    0.12
    Activations Density 0.001%

    No Known Activations