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. 65725
    Prev
    Next
    INDEX
    Explanations

    mood

    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
     ممارسة
    -0.09
     innlegg
    -0.08
     pesticides
    -0.08
    ‘zbekiston
    -0.08
     bula
    -0.08
     Obamacare
    -0.08
     percor
    -0.08
     pesticide
    -0.08
     لاع
    -0.08
     رضي
    -0.07
    POSITIVE LOGITS
     gloomy
    0.08
     serene
    0.08
     rustige
    0.08
     sombre
    0.08
     tragic
    0.08
     depict
    0.08
     portrayed
    0.08
    ampunk
    0.07
    уар
    0.07
     രംഗ
    0.07
    Activations Density 0.006%

    No Known Activations