© 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. 108437
    Prev
    Next
    INDEX
    Explanations

    steel-cut

    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
     speichern
    -0.08
    put
    -0.08
    .Runtime
    -0.08
    �
    -0.07
    饰
    -0.07
    狐
    -0.07
    幅
    -0.07
    iej
    -0.07
    anm
    -0.07
    aların
    -0.07
    POSITIVE LOGITS
     Older
    0.09
     PGA
    0.09
    Older
    0.08
     ungel
    0.08
     Petersburg
    0.08
    يقى
    0.08
     colorado
    0.08
    -з
    0.08
     Method
    0.08
     كار
    0.08
    Activations Density 0.001%

    No Known Activations