Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 1520
    Prev
    Next
    INDEX
    Explanations

    ground

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -0.09
     countries
    -0.08
     hostname
    -0.07
     mær
    -0.07
     interoperability
    -0.07
     Mack
    -0.07
     kompat
    -0.07
     skrif
    -0.07
     compatibility
    -0.07
    great
    -0.07
    POSITIVE LOGITS
    leitungen
    0.08
     medio
    0.08
    serie
    0.08
    β
    0.08
     अग
    0.08
    ngoing
    0.08
    Neu
    0.07
    连续
    0.07
    itg
    0.07
    blings
    0.07
    Activations Density 0.002%

    No Known Activations