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. 104017
    Prev
    Next
    INDEX
    Explanations

    voice-over

    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
    性生活
    -0.09
     friendships
    -0.08
     perdagangan
    -0.08
    ivik
    -0.08
    _TRI
    -0.08
     rowspan
    -0.08
     magnetic
    -0.08
    egiatan
    -0.08
    .yaml
    -0.07
    ��
    -0.07
    POSITIVE LOGITS
     speech
    0.13
    Speech
    0.12
     Speech
    0.12
     tones
    0.12
    speech
    0.12
     vowels
    0.12
     pronunciation
    0.11
     accents
    0.11
     audiobook
    0.11
    録
    0.11
    Activations Density 0.041%

    No Known Activations