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. 98696
    Prev
    Next
    INDEX
    Explanations

    Code snippets/instructions

    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
     тракт
    -0.08
     Specifically
    -0.08
     Iy
    -0.08
     honing
    -0.08
    tweets
    -0.08
     específicamente
    -0.08
    CString
    -0.07
                                                          
    -0.07
     Sarasota
    -0.07
    Subtotal
    -0.07
    POSITIVE LOGITS
     fuera
    0.08
     roku
    0.08
     باور
    0.07
     Rad
    0.07
    hp
    0.07
     era
    0.07
     outlined
    0.07
     tig
    0.07
    rad
    0.07
    095
    0.07
    Activations Density 0.014%

    No Known Activations