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. 15-RESID-POST-AA
    6. 18960
    Prev
    Next
    INDEX
    Explanations

    UTC

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    节目
    -0.08
    peater
    -0.08
     savory
    -0.08
     arts
    -0.07
     Cuban
    -0.07
     atât
    -0.07
    -shaped
    -0.07
     within
    -0.07
     facelift
    -0.07
    >
    -0.07
    POSITIVE LOGITS
     Coordin
    0.11
     UTC
    0.11
    .utc
    0.11
    .UTC
    0.09
     noon
    0.09
     אונ
    0.09
     explíc
    0.09
    .Utc
    0.08
    Pago
    0.08
    	global
    0.08
    Activations Density 0.004%

    No Known Activations