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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 96757
    Prev
    Next
    INDEX
    Explanations

    two letter tokens

    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
     hopp
    -0.09
     hopped
    -0.08
    185
    -0.08
     jne
    -0.08
    369
    -0.07
     Viert
    -0.07
     hierbei
    -0.07
     trenta
    -0.07
     ganho
    -0.07
    -Hand
    -0.07
    POSITIVE LOGITS
    I
    0.09
    aim
    0.08
    می
    0.08
     I
    0.08
     abc
    0.08
    pread
    0.08
    .Client
    0.08
    emd
    0.07
    sers
    0.07
    rafa
    0.07
    Activations Density 0.000%

    No Known Activations