© 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. 11-RESID-POST-AA
    6. 163
    Prev
    Next
    INDEX
    Explanations

    greater than/less than

    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
     retraite
    -0.09
     retire
    -0.08
     reti
    -0.08
     retired
    -0.08
     retra
    -0.08
     לאורך
    -0.08
     retiring
    -0.07
     बै
    -0.07
    融合
    -0.07
     ఎ
    -0.07
    POSITIVE LOGITS
    才能
    0.08
     disreg
    0.08
     samt
    0.08
     Sein
    0.07
     outperform
    0.07
     underm
    0.07
     Great
    0.07
    Great
    0.07
     idéal
    0.07
     Saint
    0.07
    Activations Density 0.037%

    No Known Activations