Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 54959
    Prev
    Next
    INDEX
    Explanations

    pregnant

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Grinder
    -0.08
    (pipe
    -0.08
     grinder
    -0.07
    plosion
    -0.07
    lery
    -0.07
    ยอด
    -0.07
     κοι
    -0.07
     ọdọ
    -0.07
    -gap
    -0.07
    ڳو
    -0.07
    POSITIVE LOGITS
     sample
    0.08
     cautious
    0.08
     genaue
    0.07
     દરમ
    0.07
     દરમિયાન
    0.07
     enceinte
    0.07
     दौरान
    0.07
     medic
    0.07
     sequence
    0.07
    upart
    0.07
    Activations Density 0.005%

    No Known Activations