© 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. 23-RESID-POST-AA
    6. 6531
    Prev
    Next
    INDEX
    Explanations

    detecting hate speech

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     décro
    -0.09
    icacité
    -0.09
    حال
    -0.08
     Orchestra
    -0.08
    úrg
    -0.08
     rétt
    -0.08
    ândia
    -0.08
     ಉಳ
    -0.08
     ניק
    -0.08
     حڪومت
    -0.08
    POSITIVE LOGITS
    ateful
    0.15
    ate
    0.14
    ేట్
    0.13
    േറ്റ്
    0.12
    ates
    0.11
    ATE
    0.11
     defamatory
    0.09
    ATES
    0.09
    ిం�
    0.09
    ేట
    0.09
    Activations Density 0.002%

    No Known Activations