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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 76063
    Prev
    Next
    INDEX
    Explanations

    choice

    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
     space
    -0.08
     diffuse
    -0.08
     ed
    -0.08
    Death
    -0.08
     Ed
    -0.07
     death
    -0.07
    thalm
    -0.07
     axi
    -0.07
     seda
    -0.07
    ासा
    -0.06
    POSITIVE LOGITS
    ину
    0.08
     Gerr
    0.08
     gul
    0.08
    Juego
    0.08
    Harga
    0.08
    فاوض
    0.08
    Via
    0.07
     Omdat
    0.07
     Nebraska
    0.07
    علقة
    0.07
    Activations Density 0.019%

    No Known Activations