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

    Neuronpedia

    Jacobian LensNEW
    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. 113565
    Prev
    Next
    INDEX
    Explanations

    |

    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
     inference
    -0.09
     different
    -0.07
     মাস
    -0.07
     varying
    -0.07
     માસ
    -0.07
     arb
    -0.07
    Inference
    -0.07
     ar
    -0.07
     identifiers
    -0.07
    .cached
    -0.07
    POSITIVE LOGITS
     Elena
    0.09
     Büh
    0.09
    """↵
    0.09
    _beh
    0.09
     şu
    0.09
     রয়েছে
    0.08
     Bom
    0.08
    075
    0.08
     bant
    0.08
     ретінде
    0.08
    Activations Density 0.006%

    No Known Activations