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. 130735
    Prev
    Next
    INDEX
    Explanations

    say "mm" words

    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
    leun
    -0.09
     steril
    -0.08
    film
    -0.08
     GDP
    -0.08
     nanoparticles
    -0.08
    films
    -0.08
     CNS
    -0.08
    λής
    -0.08
    CPU
    -0.08
    particle
    -0.08
    POSITIVE LOGITS
     mm
    0.16
    mm
    0.13
     мм
    0.12
    мм
    0.12
     beats
    0.11
     Beats
    0.11
     Beat
    0.11
     beat
    0.11
    -mm
    0.10
    beats
    0.10
    Activations Density 0.003%

    No Known Activations