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. 98485
    Prev
    Next
    INDEX
    Explanations

    astrophysics concepts

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    арип
    -0.10
    ડે
    -0.09
    story
    -0.09
     hevur
    -0.09
     პარტნიო
    -0.09
    াৰি
    -0.09
     outweigh
    -0.08
    ฝ่าย
    -0.08
     કમ
    -0.08
    컴
    -0.08
    POSITIVE LOGITS
     bouncing
    0.12
     bounce
    0.12
     oscill
    0.11
     Osc
    0.11
     Bounce
    0.11
    Osc
    0.10
     rotating
    0.10
    Bounce
    0.10
    bounce
    0.10
     bounced
    0.09
    Activations Density 0.004%

    No Known Activations