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. 65740
    Prev
    Next
    INDEX
    Explanations

    nya

    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
     Cell
    -0.08
     Protein
    -0.08
     Sonn
    -0.07
    _CELL
    -0.07
    ilé
    -0.07
         
    -0.07
     dort
    -0.07
    oris
    -0.07
                                        
    -0.07
     Strategy
    -0.07
    POSITIVE LOGITS
    ्र
    0.07
    מה
    0.07
    ැ
    0.07
     قوة
    0.07
     coexist
    0.07
     ballast
    0.07
    מת
    0.07
    prüche
    0.07
     بسيطة
    0.07
     فل
    0.07
    Activations Density 0.001%

    No Known Activations