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. 109801
    Prev
    Next
    INDEX
    Explanations

    line

    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
                                                                        
    -0.07
     interc
    -0.07
     segura
    -0.07
     refriger
    -0.07
    -0.07
    ített
    -0.07
     मल
    -0.07
     journ
    -0.07
                                                                      
    -0.07
     பகுத
    -0.07
    POSITIVE LOGITS
    �
    0.08
     transpl
    0.08
    -eyed
    0.08
     flank
    0.08
    _SEL
    0.07
    聚
    0.07
    .rect
    0.07
    庄
    0.07
     Component
    0.07
    什么时候
    0.07
    Activations Density 0.010%

    No Known Activations