© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 44544
    Prev
    Next
    INDEX
    Explanations

    negation

    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
     enfrenta
    -0.08
    స
    -0.08
     Wij
    -0.08
    Zw
    -0.08
    hver
    -0.08
     tackles
    -0.08
     связи
    -0.08
    uelve
    -0.08
    Wij
    -0.08
     diza
    -0.08
    POSITIVE LOGITS
     misunderstanding
    0.10
     misunderstood
    0.09
     unknow
    0.09
     subconscious
    0.09
     misleading
    0.09
     deceptive
    0.09
     mistaken
    0.09
     concealed
    0.09
     unnoticed
    0.09
     missed
    0.09
    Activations Density 0.097%

    No Known Activations