© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 1327
    Prev
    Next
    INDEX
    Explanations

    all

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     diets
    -0.07
     nim
    -0.07
     Lear
    -0.07
    507
    -0.07
    łącz
    -0.07
     attitude
    -0.07
    hton
    -0.07
     peoples
    -0.07
    hello
    -0.07
     escal
    -0.07
    POSITIVE LOGITS
    _INLINE
    0.08
     få
    0.08
     있어서
    0.08
     Taylor
    0.08
     বলে
    0.07
    0.07
    كرر
    0.07
     rex
    0.07
    这样
    0.07
     tvr
    0.07
    Activations Density 0.049%
    No Known Activations