© 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. 78079
    Prev
    Next
    INDEX
    Explanations

    Hamlet

    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
    _AX
    -0.08
     تجرب
    -0.08
     enhanced
    -0.08
     deserving
    -0.08
     disease
    -0.08
     ahaa
    -0.08
     تجربة
    -0.08
     ασφα
    -0.08
     shepherd
    -0.08
     fryer
    -0.08
    POSITIVE LOGITS
    _nm
    0.09
    523
    0.08
    Batman
    0.08
     sed
    0.08
     dí
    0.08
    Tl
    0.08
    NM
    0.07
    pele
    0.07
     IList
    0.07
    Nm
    0.07
    Activations Density 0.001%

    No Known Activations