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. 60311
    Prev
    Next
    INDEX
    Explanations

    code

    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
     flor
    -0.09
     cite
    -0.08
     cage
    -0.07
    เช
    -0.07
    沉
    -0.07
    154
    -0.07
    �
    -0.07
    ittest
    -0.07
    общ
    -0.07
     makeup
    -0.07
    POSITIVE LOGITS
    yyat
    0.08
    ə
    0.08
     Computing
    0.08
    -las
    0.08
     baz
    0.08
    ahun
    0.07
     Tsy
    0.07
     envy
    0.07
    eing
    0.07
     Frontier
    0.07
    Activations Density 0.006%

    No Known Activations