Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 43469
    Prev
    Next
    INDEX
    Explanations

    harmful

    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
     बारिश
    -0.08
     frantic
    -0.08
     goedkoop
    -0.08
     Cheapest
    -0.07
     defecto
    -0.07
     washer
    -0.07
     Bitmap
    -0.07
     crc
    -0.07
     rainfall
    -0.07
     barb
    -0.07
    POSITIVE LOGITS
    倫理
    0.12
     misinformation
    0.11
     ethical
    0.11
     токс
    0.11
     اخلاق
    0.11
     censorship
    0.11
    ethical
    0.11
     copyrighted
    0.11
     ethically
    0.11
     Ethical
    0.10
    Activations Density 0.010%

    No Known Activations