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

    Neuronpedia

    APICircuit 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. 23-RESID-POST-AA
    6. 98003
    Prev
    Next
    INDEX
    Explanations

    say "yr or av"

    np_max-act-logits · gemini-2.0-flash

    references to complex rhythmic structures in music theory.

    oai_token-act-pair · gpt-5Triggered by @liuliujiujiu05
    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
     شهادة
    -0.08
    对白
    -0.08
    นคร
    -0.08
    ститу
    -0.08
    แพ
    -0.08
     كلية
    -0.08
     PCP
    -0.07
    Purple
    -0.07
     phòng
    -0.07
    Пол
    -0.07
    POSITIVE LOGITS
    yr
    0.09
    kas
    0.09
     Network
    0.08
    ye
    0.08
     Irr
    0.08
    etheus
    0.08
    क्सर
    0.08
    Network
    0.07
     irr
    0.07
     नेटवर्क
    0.07
    Activations Density 0.000%

    No Known Activations