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. 120423
    Prev
    Next
    INDEX
    Explanations

    0

    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
     muut
    -0.09
     PERFECT
    -0.08
    sting
    -0.08
     isle
    -0.08
     muuta
    -0.07
    laş
    -0.07
     từng
    -0.07
    RESSED
    -0.07
     veranderd
    -0.07
     देने
    -0.07
    POSITIVE LOGITS
     ರಿಂದ
    0.08
    ️⃣
    0.08
    洞
    0.08
     నుం�
    0.07
     Elliott
    0.07
    .shadow
    0.07
     percurso
    0.07
     నుండి
    0.07
    ″
    0.07
     Mari
    0.07
    Activations Density 0.011%

    No Known Activations