© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 95039
    Prev
    Next
    INDEX
    Explanations

    part

    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
    Walk
    -0.08
     Walk
    -0.08
    elje
    -0.08
    MORE
    -0.08
    Notas
    -0.08
     walk
    -0.08
     Leder
    -0.08
    zijn
    -0.07
     ćemo
    -0.07
     jó
    -0.07
    POSITIVE LOGITS
     wiederum
    0.10
     itself
    0.08
     ::=
    0.08
     themselves
    0.08
     officials
    0.08
     also
    0.07
     thus
    0.07
     также
    0.07
     electromagnetic
    0.07
     أيضًا
    0.07
    Activations Density 0.155%

    No Known Activations