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. 112769
    Prev
    Next
    INDEX
    Explanations

    representation

    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
     indications
    -0.09
    Ahmed
    -0.08
     establishes
    -0.08
    serv
    -0.08
     responders
    -0.08
     autonomy
    -0.07
    maßnahmen
    -0.07
     cath
    -0.07
     criterios
    -0.07
     hygiene
    -0.07
    POSITIVE LOGITS
     రూప
    0.08
     hank
    0.07
     succinct
    0.07
     Darstellung
    0.07
    FB
    0.07
     Problems
    0.07
    Four
    0.07
     coloc
    0.07
    ทาง
    0.07
    áid
    0.07
    Activations Density 0.009%

    No Known Activations