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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 49136
    Prev
    Next
    INDEX
    Explanations

    syntax

    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
    连
    -0.08
    ឹង
    -0.08
    ituksen
    -0.07
    raiser
    -0.07
    ியில்
    -0.07
     '.')
    -0.07
    Todd
    -0.07
     workshop
    -0.07
     decking
    -0.07
     hostel
    -0.07
    POSITIVE LOGITS
     syntax
    0.12
     ::=
    0.12
     lautet
    0.12
    yntax
    0.11
     Syntax
    0.11
    Syntax
    0.10
    Generally
    0.10
    сис
    0.09
     Generally
    0.09
     générale
    0.09
    Activations Density 0.012%

    No Known Activations