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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 1146
    Prev
    Next
    INDEX
    Explanations

    cos

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pend
    -0.08
     mortar
    -0.08
     مط
    -0.07
     Supervisor
    -0.07
    maschine
    -0.07
    ")↵↵↵
    -0.07
     counterpart
    -0.07
    <Void
    -0.07
     발표
    -0.07
     oddly
    -0.07
    POSITIVE LOGITS
     Algarve
    0.08
    ,map
    0.08
     hypers
    0.07
     Haf
    0.07
     DPR
    0.07
    HS
    0.07
     THC
    0.07
     entertained
    0.07
    roch
    0.07
     Universal
    0.07
    Activations Density 0.029%

    No Known Activations