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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 68465
    Prev
    Next
    INDEX
    Explanations

    7

    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
    polygon
    -0.10
     polygon
    -0.09
     PRIME
    -0.09
     Seoul
    -0.08
     Taipei
    -0.08
     svet
    -0.08
     Bratis
    -0.08
     curves
    -0.08
     SNP
    -0.08
     polygons
    -0.07
    POSITIVE LOGITS
     прес
    0.08
    _assoc
    0.08
    杂
    0.08
     Bö
    0.08
     booklet
    0.08
    _bw
    0.08
    Gam
    0.07
     noises
    0.07
     kling
    0.07
    -feedback
    0.07
    Activations Density 0.000%

    No Known Activations