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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 78537
    Prev
    Next
    INDEX
    Explanations

    Timer

    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
    ätigung
    -0.09
    wonder
    -0.08
     kod
    -0.08
     cigarettes
    -0.08
     bedenken
    -0.08
     rakent
    -0.08
     teilnehmen
    -0.07
     nät
    -0.07
    Bachelor
    -0.07
    club
    -0.07
    POSITIVE LOGITS
     componente
    0.08
     ...(
    0.08
    EM
    0.08
     parm
    0.08
     Suprema
    0.07
     opts
    0.07
    itten
    0.07
     miseric
    0.07
     Văn
    0.07
     EMS
    0.07
    Activations Density 0.001%

    No Known Activations