© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 49995
    Prev
    Next
    INDEX
    Explanations

    say "ch" 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
     приобр
    -0.09
    acious
    -0.08
     первых
    -0.07
    icago
    -0.07
    ിയാണ്
    -0.07
     sonho
    -0.07
    rossover
    -0.07
    ούς
    -0.07
     depth
    -0.07
     zvek
    -0.07
    POSITIVE LOGITS
    ch
    0.14
    ceria
    0.13
    chet
    0.12
    chito
    0.12
    china
    0.12
    cher
    0.11
    chon
    0.11
    CH
    0.11
    chi
    0.11
    chia
    0.11
    Activations Density 0.002%

    No Known Activations