© 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. 11-RESID-POST-AA
    11. 24680
    Prev
    Next
    INDEX
    Explanations

    is

    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
    шин
    -0.10
     Flats
    -0.09
     Nase
    -0.09
    县
    -0.08
    鑫
    -0.08
    (poly
    -0.08
     Dale
    -0.08
     Cina
    -0.08
    _polygon
    -0.08
     tyre
    -0.08
    POSITIVE LOGITS
     സ്
    0.08
    ണ്ട
    0.08
     നടത്ത
    0.08
     meuble
    0.08
    نى
    0.08
     replic
    0.07
     meubles
    0.07
     transcripts
    0.07
     meub
    0.07
    യ്
    0.07
    Activations Density 0.001%

    No Known Activations