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. 15-RESID-POST-AA
    6. 19052
    Prev
    Next
    INDEX
    Explanations

    mathematical proofs

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     horoscope
    -0.09
    ികച്ച
    -0.08
    �
    -0.08
     nghỉ
    -0.08
    辨
    -0.08
     devotional
    -0.08
     väik
    -0.08
    メリ
    -0.08
    純
    -0.07
    纯
    -0.07
    POSITIVE LOGITS
    ']↵↵
    0.09
    '];
    0.08
     contradiction
    0.08
    Lemma
    0.08
    '];↵↵
    0.08
    viol
    0.08
    ]',
    0.08
     impat
    0.08
    '];↵
    0.08
     blocking
    0.07
    Activations Density 0.005%

    No Known Activations