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. 24427
    Prev
    Next
    INDEX
    Explanations

    Math expressions

    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
     VID
    -0.08
     Bouw
    -0.08
     anglais
    -0.08
     ei
    -0.08
     অ
    -0.08
     nex
    -0.08
     ಸಾಲ
    -0.07
     boya
    -0.07
     PID
    -0.07
     n
    -0.07
    POSITIVE LOGITS
    artu
    0.09
    verein
    0.08
     mountainous
    0.08
     esquerda
    0.08
    bereich
    0.08
     Jurassic
    0.08
    arty
    0.07
     glanced
    0.07
     Hort
    0.07
     Verein
    0.07
    Activations Density 0.095%

    No Known Activations