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. 27612
    Prev
    Next
    INDEX
    Explanations

    peak demand

    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
     terminado
    -0.09
    Evidence
    -0.08
     Evidence
    -0.08
     políticos
    -0.08
     μέχρι
    -0.08
     예정이다
    -0.07
    _polygon
    -0.07
     dispers
    -0.07
    pol
    -0.07
     Evid
    -0.07
    POSITIVE LOGITS
     peak
    0.15
    Peak
    0.14
     Peak
    0.14
     peaks
    0.14
    _peak
    0.13
    峰
    0.13
     �
    0.12
     Peaks
    0.12
    peak
    0.11
     нагрузки
    0.10
    Activations Density 0.004%

    No Known Activations