© 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. 63251
    Prev
    Next
    INDEX
    Explanations

    bad movies

    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
    μμα
    -0.08
     actualmente
    -0.08
    ovima
    -0.08
    વાનું
    -0.08
    panelen
    -0.08
     docks
    -0.08
    	lib
    -0.08
     diversi
    -0.08
    lib
    -0.08
    כמה
    -0.08
    POSITIVE LOGITS
     awkward
    0.12
     ridiculous
    0.10
     misuse
    0.10
     absurd
    0.10
     atroc
    0.10
     disastrous
    0.10
     गलत
    0.09
     quirky
    0.09
    Illegal
    0.09
     poorly
    0.09
    Activations Density 0.074%

    No Known Activations