Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 2408
    Prev
    Next
    INDEX
    Explanations

    above

    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
    RT
    -0.09
     Oregon
    -0.07
    HO
    -0.07
    priv
    -0.07
    idle
    -0.07
    hos
    -0.07
    ha
    -0.07
    pilot
    -0.07
    jour
    -0.07
    avi
    -0.07
    POSITIVE LOGITS
    서
    0.09
    소드
    0.08
    wars
    0.07
    서를
    0.07
    分别
    0.07
     przeb
    0.07
     Edmund
    0.07
     примерно
    0.07
     PRIME
    0.07
    喝
    0.07
    Activations Density 0.004%

    No Known Activations