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. 58807
    Prev
    Next
    INDEX
    Explanations

    falls

    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
     Parkinson
    -0.09
     paseo
    -0.08
     Bein
    -0.07
    perfil
    -0.07
     Dayton
    -0.07
     hipot
    -0.07
     �
    -0.07
    ireo
    -0.07
     descul
    -0.07
    😊
    -0.07
    POSITIVE LOGITS
    ILogger
    0.08
    क्षित
    0.08
     भ्रष्ट
    0.08
     Plac
    0.08
    ดำ
    0.08
    Plac
    0.08
     वार
    0.08
     zip
    0.08
     verniet
    0.08
     rouges
    0.08
    Activations Density 0.006%

    No Known Activations