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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 111834
    Prev
    Next
    INDEX
    Explanations

    Responding to letter inputs

    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
     السكان
    -0.08
    bulk
    -0.08
     площадь
    -0.08
     المستثمر
    -0.08
    贷
    -0.08
     presso
    -0.07
    .Math
    -0.07
     kredit
    -0.07
     확보
    -0.07
     ymax
    -0.07
    POSITIVE LOGITS
     halluc
    0.11
     Emoji
    0.10
     Emo
    0.10
     emojis
    0.10
     unsolicited
    0.09
     Literal
    0.09
    Emoji
    0.09
     silently
    0.09
    Alphabet
    0.09
     alphabetical
    0.09
    Activations Density 0.024%

    No Known Activations