© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 1507
    Prev
    Next
    INDEX
    Explanations

    with

    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
     Tut
    -0.09
    ADO
    -0.08
     computed
    -0.08
     produced
    -0.07
    ado
    -0.07
     tunnel
    -0.07
     patients
    -0.07
    ################
    -0.07
    <'
    -0.07
     pili
    -0.07
    POSITIVE LOGITS
     strumenti
    0.09
    打造
    0.08
    nyama
    0.08
     (:
    0.08
    盆
    0.08
    erva
    0.08
    闪
    0.08
    త్
    0.08
    preis
    0.08
    不限
    0.08
    Activations Density 0.005%

    No Known Activations