Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 75328
    Prev
    Next
    INDEX
    Explanations

    receptor

    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
    reflection
    -0.08
     resist
    -0.08
     resistor
    -0.07
    uous
    -0.07
    Cant
    -0.07
     carácter
    -0.07
    rapid
    -0.07
    dır
    -0.07
     cript
    -0.07
    /cr
    -0.07
    POSITIVE LOGITS
     dib
    0.08
     Pemb
    0.08
     Cleaner
    0.08
     장
    0.08
     barg
    0.08
     pemb
    0.08
     saham
    0.08
     poin
    0.07
     Dib
    0.07
    正在
    0.07
    Activations Density 0.003%

    No Known Activations