© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 96709
    Prev
    Next
    INDEX
    Explanations

    Our

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -E
    -0.09
    =(
    -0.08
     =(
    -0.08
    ='%
    -0.08
    =id
    -0.08
     ಠ
    -0.08
    -se
    -0.08
     পারেন
    -0.08
    ='
    -0.08
    -name
    -0.08
    POSITIVE LOGITS
     avons
    0.10
     devons
    0.10
     নিজেদের
    0.10
    ಿಬ್ಬ
    0.10
    카지노
    0.10
     можем
    0.10
    -mêmes
    0.10
     discussion
    0.09
     finest
    0.09
     sentimos
    0.09
    Activations Density 0.097%

    No Known Activations