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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 9257
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .Type
    -0.09
    <Type
    -0.09
     stamps
    -0.09
    (Type
    -0.08
     textures
    -0.08
     vowels
    -0.08
     fillers
    -0.08
     caracteres
    -0.08
     buds
    -0.07
     Eta
    -0.07
    POSITIVE LOGITS
    <|endoftext|>
    0.11
    <|reserved_200016|>
    0.10
     কৰিছে
    0.08
     Kep
    0.07
     keb
    0.07
     গবেষ
    0.07
     Purch
    0.07
     NGO
    0.07
     :=↵
    0.07
    Purch
    0.07
    Activations Density 0.583%

    No Known Activations