© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 102938
    Prev
    Next
    INDEX
    Explanations

    Studying and analyzing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     it'll
    -0.11
     può
    -0.11
     يمكنك
    -0.11
     even
    -0.11
    even
    -0.11
     puede
    -0.10
     может
    -0.10
     peut
    -0.10
     you'll
    -0.10
     infatti
    -0.10
    POSITIVE LOGITS
     examined
    0.15
     assessed
    0.15
    进行了
    0.14
     analyzed
    0.14
     investigated
    0.13
     analysed
    0.12
     examining
    0.12
     were
    0.12
     assessing
    0.12
     untersucht
    0.12
    Activations Density 0.031%

    No Known Activations