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. 30801
    Prev
    Next
    INDEX
    Explanations

    code formatting

    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
     recopil
    -0.08
     motives
    -0.08
     recruitment
    -0.07
    院
    -0.07
    ��
    -0.07
    ritter
    -0.07
     chore
    -0.07
     upgrades
    -0.07
     javafx
    -0.07
    _mutex
    -0.07
    POSITIVE LOGITS
    Exp
    0.10
    ’exp
    0.09
    _EXP
    0.09
    exp
    0.09
    (dictionary
    0.09
     exp
    0.09
    'exp
    0.09
    Expired
    0.09
     Exp
    0.09
    Overflow
    0.09
    Activations Density 0.008%

    No Known Activations