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. 54386
    Prev
    Next
    INDEX
    Explanations

    stories

    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
     honing
    -0.08
     tested
    -0.08
     Tested
    -0.08
    tested
    -0.08
     сверх
    -0.08
    .converter
    -0.08
    Six
    -0.08
    Docs
    -0.08
    .dist
    -0.08
    	protected
    -0.08
    POSITIVE LOGITS
     recognizable
    0.09
    -themed
    0.08
     apology
    0.08
     kurzen
    0.08
     Inhalt
    0.08
    inama
    0.08
     hap
    0.08
     sentences
    0.08
    寓
    0.07
     verk
    0.07
    Activations Density 0.032%

    No Known Activations