© 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 EvalsExportsinterp-engineNEWAPI 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. 51833
    Prev
    Next
    INDEX
    Explanations

    言

    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
    zky
    -0.09
    rn
    -0.08
    Anc
    -0.08
    ed
    -0.08
    snd
    -0.08
    sj
    -0.08
    zd
    -0.07
    рыл
    -0.07
    chn
    -0.07
    md
    -0.07
    POSITIVE LOGITS
    う
    0.35
    い
    0.34
    います
    0.32
    えば
    0.31
    いました
    0.30
    った
    0.30
    われ
    0.30
    える
    0.28
    って
    0.26
    いや
    0.23
    Activations Density 0.003%

    No Known Activations