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. 52967
    Prev
    Next
    INDEX
    Explanations

    Chinese poetry

    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
     näky
    -0.08
     રસ્ત
    -0.08
     રોડ
    -0.08
     tegn
    -0.08
     DCHECK
    -0.07
     અનુ
    -0.07
     connaît
    -0.07
     branches
    -0.07
    ální
    -0.07
    assist
    -0.07
    POSITIVE LOGITS
     песни
    0.10
     गीत
    0.09
     ಹಾಡ
    0.09
    เพลง
    0.09
    歌曲
    0.09
     sung
    0.09
    (_,
    0.09
    Hotel
    0.09
     Sonata
    0.08
    .music
    0.08
    Activations Density 0.001%

    No Known Activations