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. 30802
    Prev
    Next
    INDEX
    Explanations

    destination

    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
    788
    -0.08
    antal
    -0.07
    falls
    -0.07
    ума
    -0.07
     น้ำ
    -0.07
    	rows
    -0.07
    827
    -0.07
     envelope
    -0.07
    în
    -0.07
    unna
    -0.07
    POSITIVE LOGITS
    老虎机
    0.09
     surgery
    0.08
    式
    0.08
    medicine
    0.08
     medicine
    0.08
     fucking
    0.08
     yoga
    0.08
     Edition
    0.08
    สล็อต
    0.07
     терапии
    0.07
    Activations Density 0.276%

    No Known Activations