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. 103263
    Prev
    Next
    INDEX
    Explanations

    butter

    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
    ATABASE
    -0.08
     تب
    -0.08
    息
    -0.08
    Privileges
    -0.08
     bire
    -0.08
     amphib
    -0.08
    	fi
    -0.08
     Nieuw
    -0.07
    Shaders
    -0.07
     privind
    -0.07
    POSITIVE LOGITS
     સોશિયલ
    0.08
    车
    0.08
     ZIP
    0.08
     dunk
    0.08
    ucr
    0.08
     wrestling
    0.07
    柜
    0.07
     nutrit
    0.07
     Resist
    0.07
     waffle
    0.07
    Activations Density 0.002%

    No Known Activations