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. 104135
    Prev
    Next
    INDEX
    Explanations

    Reasoning direction

    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
    ení
    -0.09
     تعط
    -0.09
     признаки
    -0.08
     alasan
    -0.08
     מוש
    -0.08
     kus
    -0.07
    kleur
    -0.07
    kus
    -0.07
     مز
    -0.07
     在
    -0.07
    POSITIVE LOGITS
     गति
    0.10
     speed
    0.08
     transitions
    0.08
     sped
    0.08
    wärts
    0.08
     slower
    0.08
     forwards
    0.07
     wavelength
    0.07
    Cartesian
    0.07
    Inbound
    0.07
    Activations Density 0.009%

    No Known Activations