© 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 EvalsExportsinterp-engineNEWAPI 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. 110568
    Prev
    Next
    INDEX
    Explanations

    Blackjack

    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
     infamous
    -0.08
     effects
    -0.08
     asymmetric
    -0.07
     cafe
    -0.07
     causal
    -0.07
     slang
    -0.07
     efectos
    -0.07
     terrific
    -0.07
     title
    -0.07
     iconic
    -0.07
    POSITIVE LOGITS
     söyle
    0.10
     Telefonnummer
    0.08
    236
    0.08
    _break
    0.08
     Mere
    0.08
    .mapping
    0.08
     лап
    0.08
     Dy
    0.08
     Meinung
    0.08
    ″
    0.08
    Activations Density 0.001%

    No Known Activations