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. 78663
    Prev
    Next
    INDEX
    Explanations

    sqrt

    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
     Pfe
    -0.09
    уют
    -0.08
    ادگی
    -0.08
    	field
    -0.08
    	Field
    -0.08
     */↵↵↵
    -0.08
    ");↵↵↵
    -0.08
     hasi
    -0.08
     */;↵
    -0.07
     tabletop
    -0.07
    POSITIVE LOGITS
    ječ
    0.08
     Roth
    0.08
    pard
    0.08
    den
    0.07
    best
    0.07
    @qq
    0.07
    цем
    0.07
     sworn
    0.07
    耀
    0.07
    inum
    0.07
    Activations Density 0.019%

    No Known Activations