© 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. 50935
    Prev
    Next
    INDEX
    Explanations

    rot

    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
    باع
    -0.10
     nar
    -0.09
    stvo
    -0.09
    ноп
    -0.09
    thy
    -0.08
    ianik
    -0.08
    ství
    -0.08
    ရွိ
    -0.08
    નવી
    -0.08
    ẵn
    -0.08
    POSITIVE LOGITS
    ic
    0.15
    IC
    0.10
    izing
    0.09
    iform
    0.09
    ensin
    0.09
    ropic
    0.08
    rop
    0.08
     ic
    0.08
     meth
    0.08
    oxic
    0.08
    Activations Density 0.003%

    No Known Activations