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

    Neuronpedia

    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. 96361
    Prev
    Next
    INDEX
    Explanations

    say "ach" 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
    �
    -0.09
    idunt
    -0.09
    Stan
    -0.08
    .station
    -0.08
     serieus
    -0.07
    imali
    -0.07
    druk
    -0.07
    zeker
    -0.07
    veyor
    -0.07
    ueling
    -0.07
    POSITIVE LOGITS
    aching
    0.22
    aches
    0.20
    ach
    0.19
    achment
    0.18
    ACH
    0.17
    atch
    0.16
    ాచ్
    0.16
    achable
    0.15
    achers
    0.15
    achto
    0.14
    Activations Density 0.001%

    No Known Activations