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. 76292
    Prev
    Next
    INDEX
    Explanations

    Isaiah

    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
     Weak
    -0.08
     potassium
    -0.08
     कमजोर
    -0.08
     Compet
    -0.08
     bal
    -0.08
     baja
    -0.08
     bibliography
    -0.08
     bears
    -0.07
     ആ
    -0.07
    	friend
    -0.07
    POSITIVE LOGITS
     depicts
    0.07
    ftware
    0.07
    лица
    0.07
    енд
    0.07
    Allows
    0.07
    Tod
    0.07
    -logo
    0.07
    ್ದ
    0.07
     undoubtedly
    0.07
     majest
    0.07
    Activations Density 0.002%

    No Known Activations